Files
oh-my-pi/packages/catalog/src/models.json
T
can1357 d4317d3d20 feat(ai): consolidated OpenAI-family streaming and add OpenRouter API support
This change introduces a new `openrouter` API type and extensively refactors OpenAI-family streaming providers, centralizing shared logic and improving robustness.

Key changes include:
- **Unified OpenAI-family Logic:** Consolidated core utilities, compat resolution, request shaping, and stream processing into `openai-shared.ts`, reducing duplication across `openai-completions`, `openai-responses`, and `openai-codex-responses`.
- **OpenRouter API Type:** Introduced a dedicated `openrouter` API type with dual-surface compatibility, allowing it to dispatch requests as either OpenAI Chat Completions or Responses.
- **Enhanced Provider Integration:**
    - Improved Perplexity search to leverage shared OpenAI streaming transports, including API-key fallback to OpenRouter and support for Perplexity's Responses API.
    - Integrated xAI-specific logic directly into the shared `stream.ts` dispatch, removing the dedicated `xai-responses` provider.
    - Refined credential parsing for Google Gemini CLI and handling of Azure deployment names.
- **Robustness & Consistency:** Improved error handling for Codex, standardized output token parameter resolution, and ensured consistent application of reasoning suppression across all Chat Completions dialects.
- **New Documentation:** Added `provider-endpoint-constraints.md` to detail endpoint-specific behaviors and quirks for various providers.
- **Telemetry & Debugging:** Extended telemetry propagation to advisor calls and overflow compaction tasks. Improved debugging for Codex WebSocket failures and stream error messages.
- **Tooling & Security:** Updated browser stealth scripts to prevent detection and added a new `ts-no-inline-cast-access` TTSR rule.
2026-06-17 21:36:48 +02:00

84026 lines
1.6 MiB
Plaintext

{
"aimlapi": {
"act_two": {
"id": "act_two",
"name": "act_two",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"alibaba/qwen-max": {
"id": "alibaba/qwen-max",
"name": "alibaba/qwen-max",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"alibaba/qwen-plus": {
"id": "alibaba/qwen-plus",
"name": "alibaba/qwen-plus",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"alibaba/qwen-turbo": {
"id": "alibaba/qwen-turbo",
"name": "alibaba/qwen-turbo",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"alibaba/qwen3-235b-a22b-thinking-2507": {
"id": "alibaba/qwen3-235b-a22b-thinking-2507",
"name": "alibaba/qwen3-235b-a22b-thinking-2507",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"alibaba/qwen3-32b": {
"id": "alibaba/qwen3-32b",
"name": "alibaba/qwen3-32b",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 40960
},
"alibaba/qwen3-coder-480b-a35b-instruct": {
"id": "alibaba/qwen3-coder-480b-a35b-instruct",
"name": "alibaba/qwen3-coder-480b-a35b-instruct",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 8192
},
"alibaba/qwen3-max-instruct": {
"id": "alibaba/qwen3-max-instruct",
"name": "alibaba/qwen3-max-instruct",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"alibaba/qwen3-next-80b-a3b-instruct": {
"id": "alibaba/qwen3-next-80b-a3b-instruct",
"name": "alibaba/qwen3-next-80b-a3b-instruct",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 16384
},
"alibaba/qwen3-next-80b-a3b-thinking": {
"id": "alibaba/qwen3-next-80b-a3b-thinking",
"name": "alibaba/qwen3-next-80b-a3b-thinking",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768
},
"alibaba/wan2.2-14b-animate-move": {
"id": "alibaba/wan2.2-14b-animate-move",
"name": "alibaba/wan2.2-14b-animate-move",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"alibaba/wan2.2-14b-animate-replace": {
"id": "alibaba/wan2.2-14b-animate-replace",
"name": "alibaba/wan2.2-14b-animate-replace",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"alibaba/wan2.2-vace-fun-a14b-depth": {
"id": "alibaba/wan2.2-vace-fun-a14b-depth",
"name": "alibaba/wan2.2-vace-fun-a14b-depth",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"alibaba/wan2.2-vace-fun-a14b-inpainting": {
"id": "alibaba/wan2.2-vace-fun-a14b-inpainting",
"name": "alibaba/wan2.2-vace-fun-a14b-inpainting",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"alibaba/wan2.2-vace-fun-a14b-outpainting": {
"id": "alibaba/wan2.2-vace-fun-a14b-outpainting",
"name": "alibaba/wan2.2-vace-fun-a14b-outpainting",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"alibaba/wan2.2-vace-fun-a14b-pose": {
"id": "alibaba/wan2.2-vace-fun-a14b-pose",
"name": "alibaba/wan2.2-vace-fun-a14b-pose",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"alibaba/wan2.2-vace-fun-a14b-reframe": {
"id": "alibaba/wan2.2-vace-fun-a14b-reframe",
"name": "alibaba/wan2.2-vace-fun-a14b-reframe",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-amalthea-en": {
"id": "aura-2-amalthea-en",
"name": "aura-2-amalthea-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-andromeda-en": {
"id": "aura-2-andromeda-en",
"name": "aura-2-andromeda-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-apollo-en": {
"id": "aura-2-apollo-en",
"name": "aura-2-apollo-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-arcas-en": {
"id": "aura-2-arcas-en",
"name": "aura-2-arcas-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-aries-en": {
"id": "aura-2-aries-en",
"name": "aura-2-aries-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-asteria-en": {
"id": "aura-2-asteria-en",
"name": "aura-2-asteria-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-athena-en": {
"id": "aura-2-athena-en",
"name": "aura-2-athena-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-atlas-en": {
"id": "aura-2-atlas-en",
"name": "aura-2-atlas-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-aurora-en": {
"id": "aura-2-aurora-en",
"name": "aura-2-aurora-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-callista-en": {
"id": "aura-2-callista-en",
"name": "aura-2-callista-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-celeste-es": {
"id": "aura-2-celeste-es",
"name": "aura-2-celeste-es",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-cora-en": {
"id": "aura-2-cora-en",
"name": "aura-2-cora-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-cordelia-en": {
"id": "aura-2-cordelia-en",
"name": "aura-2-cordelia-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-delia-en": {
"id": "aura-2-delia-en",
"name": "aura-2-delia-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-draco-en": {
"id": "aura-2-draco-en",
"name": "aura-2-draco-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-electra-en": {
"id": "aura-2-electra-en",
"name": "aura-2-electra-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-estrella-es": {
"id": "aura-2-estrella-es",
"name": "aura-2-estrella-es",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-harmonia-en": {
"id": "aura-2-harmonia-en",
"name": "aura-2-harmonia-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-helena-en": {
"id": "aura-2-helena-en",
"name": "aura-2-helena-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-hera-en": {
"id": "aura-2-hera-en",
"name": "aura-2-hera-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-hermes-en": {
"id": "aura-2-hermes-en",
"name": "aura-2-hermes-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-hyperion-en": {
"id": "aura-2-hyperion-en",
"name": "aura-2-hyperion-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-iris-en": {
"id": "aura-2-iris-en",
"name": "aura-2-iris-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-janus-en": {
"id": "aura-2-janus-en",
"name": "aura-2-janus-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-juno-en": {
"id": "aura-2-juno-en",
"name": "aura-2-juno-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-jupiter-en": {
"id": "aura-2-jupiter-en",
"name": "aura-2-jupiter-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-luna-en": {
"id": "aura-2-luna-en",
"name": "aura-2-luna-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-mars-en": {
"id": "aura-2-mars-en",
"name": "aura-2-mars-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-minerva-en": {
"id": "aura-2-minerva-en",
"name": "aura-2-minerva-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-neptune-en": {
"id": "aura-2-neptune-en",
"name": "aura-2-neptune-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-nestor-es": {
"id": "aura-2-nestor-es",
"name": "aura-2-nestor-es",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-odysseus-en": {
"id": "aura-2-odysseus-en",
"name": "aura-2-odysseus-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-ophelia-en": {
"id": "aura-2-ophelia-en",
"name": "aura-2-ophelia-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-orion-en": {
"id": "aura-2-orion-en",
"name": "aura-2-orion-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-orpheus-en": {
"id": "aura-2-orpheus-en",
"name": "aura-2-orpheus-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-pandora-en": {
"id": "aura-2-pandora-en",
"name": "aura-2-pandora-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-phoebe-en": {
"id": "aura-2-phoebe-en",
"name": "aura-2-phoebe-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-pluto-en": {
"id": "aura-2-pluto-en",
"name": "aura-2-pluto-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-saturn-en": {
"id": "aura-2-saturn-en",
"name": "aura-2-saturn-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-selene-en": {
"id": "aura-2-selene-en",
"name": "aura-2-selene-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-thalia-en": {
"id": "aura-2-thalia-en",
"name": "aura-2-thalia-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-theia-en": {
"id": "aura-2-theia-en",
"name": "aura-2-theia-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-vesta-en": {
"id": "aura-2-vesta-en",
"name": "aura-2-vesta-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-2-zeus-en": {
"id": "aura-2-zeus-en",
"name": "aura-2-zeus-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-angus-en": {
"id": "aura-angus-en",
"name": "aura-angus-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-arcas-en": {
"id": "aura-arcas-en",
"name": "aura-arcas-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-asteria-en": {
"id": "aura-asteria-en",
"name": "aura-asteria-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-athena-en": {
"id": "aura-athena-en",
"name": "aura-athena-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-helios-en": {
"id": "aura-helios-en",
"name": "aura-helios-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-hera-en": {
"id": "aura-hera-en",
"name": "aura-hera-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-luna-en": {
"id": "aura-luna-en",
"name": "aura-luna-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-orion-en": {
"id": "aura-orion-en",
"name": "aura-orion-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-orpheus-en": {
"id": "aura-orpheus-en",
"name": "aura-orpheus-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-perseus-en": {
"id": "aura-perseus-en",
"name": "aura-perseus-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-stella-en": {
"id": "aura-stella-en",
"name": "aura-stella-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aura-zeus-en": {
"id": "aura-zeus-en",
"name": "aura-zeus-en",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"baidu/ernie-4-5-0-3b": {
"id": "baidu/ernie-4-5-0-3b",
"name": "baidu/ernie-4-5-0-3b",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"baidu/ernie-4-5-21b-a3b": {
"id": "baidu/ernie-4-5-21b-a3b",
"name": "baidu/ernie-4-5-21b-a3b",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortRouting": {
"off": "baidu/ernie-4-5-21b-a3b",
"minimal": "baidu/ernie-4-5-21b-a3b-thinking",
"low": "baidu/ernie-4-5-21b-a3b-thinking",
"medium": "baidu/ernie-4-5-21b-a3b-thinking",
"high": "baidu/ernie-4-5-21b-a3b-thinking",
"xhigh": "baidu/ernie-4-5-21b-a3b-thinking"
}
}
},
"baidu/ernie-4-5-300b-a47b": {
"id": "baidu/ernie-4-5-300b-a47b",
"name": "baidu/ernie-4-5-300b-a47b",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"baidu/ernie-4-5-300b-a47b-paddle": {
"id": "baidu/ernie-4-5-300b-a47b-paddle",
"name": "baidu/ernie-4-5-300b-a47b-paddle",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"baidu/ernie-4-5-8k-preview": {
"id": "baidu/ernie-4-5-8k-preview",
"name": "baidu/ernie-4-5-8k-preview",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"baidu/ernie-4-5-turbo-128k": {
"id": "baidu/ernie-4-5-turbo-128k",
"name": "baidu/ernie-4-5-turbo-128k",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"baidu/ernie-4-5-turbo-vl-32k": {
"id": "baidu/ernie-4-5-turbo-vl-32k",
"name": "baidu/ernie-4-5-turbo-vl-32k",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"baidu/ernie-4-5-vl-28b-a3b": {
"id": "baidu/ernie-4-5-vl-28b-a3b",
"name": "baidu/ernie-4-5-vl-28b-a3b",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8000
},
"baidu/ernie-4-5-vl-424b-a47b": {
"id": "baidu/ernie-4-5-vl-424b-a47b",
"name": "baidu/ernie-4-5-vl-424b-a47b",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"baidu/ernie-5-0-thinking-latest": {
"id": "baidu/ernie-5-0-thinking-latest",
"name": "baidu/ernie-5-0-thinking-latest",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"baidu/ernie-5-0-thinking-preview": {
"id": "baidu/ernie-5-0-thinking-preview",
"name": "baidu/ernie-5-0-thinking-preview",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 64000
},
"baidu/ernie-x1-1-preview": {
"id": "baidu/ernie-x1-1-preview",
"name": "baidu/ernie-x1-1-preview",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 65536,
"maxTokens": null
},
"baidu/ernie-x1-turbo-32k": {
"id": "baidu/ernie-x1-turbo-32k",
"name": "baidu/ernie-x1-turbo-32k",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"bytedance/dreamina-creative-upscale": {
"id": "bytedance/dreamina-creative-upscale",
"name": "bytedance/dreamina-creative-upscale",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"bytedance/dreamina-seedance-2-0": {
"id": "bytedance/dreamina-seedance-2-0",
"name": "bytedance/dreamina-seedance-2-0",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"bytedance/dreamina-seedance-2-0-fast": {
"id": "bytedance/dreamina-seedance-2-0-fast",
"name": "bytedance/dreamina-seedance-2-0-fast",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"bytedance/omnihuman": {
"id": "bytedance/omnihuman",
"name": "bytedance/omnihuman",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"bytedance/omnihuman/v1.5": {
"id": "bytedance/omnihuman/v1.5",
"name": "bytedance/omnihuman/v1.5",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"bytedance/seed-1-8": {
"id": "bytedance/seed-1-8",
"name": "bytedance/seed-1-8",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"bytedance/seed-2-0-code-preview": {
"id": "bytedance/seed-2-0-code-preview",
"name": "bytedance/seed-2-0-code-preview",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"bytedance/seed-2-0-lite": {
"id": "bytedance/seed-2-0-lite",
"name": "bytedance/seed-2-0-lite",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"bytedance/seed-2-0-mini": {
"id": "bytedance/seed-2-0-mini",
"name": "bytedance/seed-2-0-mini",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"bytedance/seed-2-0-pro": {
"id": "bytedance/seed-2-0-pro",
"name": "bytedance/seed-2-0-pro",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"bytedance/seedance-1-0-pro": {
"id": "bytedance/seedance-1-0-pro",
"name": "bytedance/seedance-1-0-pro",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"bytedance/seedance-1-0-pro-fast": {
"id": "bytedance/seedance-1-0-pro-fast",
"name": "bytedance/seedance-1-0-pro-fast",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"bytedance/seedance-1-5-pro": {
"id": "bytedance/seedance-1-5-pro",
"name": "bytedance/seedance-1-5-pro",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"bytedance/seedance-2-0": {
"id": "bytedance/seedance-2-0",
"name": "bytedance/seedance-2-0",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"bytedance/seedance-2-0-fast": {
"id": "bytedance/seedance-2-0-fast",
"name": "bytedance/seedance-2-0-fast",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"bytedance/seedream-4-5": {
"id": "bytedance/seedream-4-5",
"name": "bytedance/seedream-4-5",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"bytedance/seedream-5-0-lite": {
"id": "bytedance/seedream-5-0-lite",
"name": "bytedance/seedream-5-0-lite",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"bytedance/seedream/v4/edit": {
"id": "bytedance/seedream/v4/edit",
"name": "bytedance/seedream/v4/edit",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"claude-haiku-4-5-20251001": {
"id": "claude-haiku-4-5-20251001",
"name": "Claude Haiku 4.5",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-opus-4-1-20250805": {
"id": "claude-opus-4-1-20250805",
"name": "Claude Opus 4.1",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-opus-4-20250514": {
"id": "claude-opus-4-20250514",
"name": "Claude Opus 4",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-opus-4-5-20251101": {
"id": "claude-opus-4-5-20251101",
"name": "Claude Opus 4.5",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-opus-4-6": {
"id": "claude-opus-4-6",
"name": "Claude Opus 4.6",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-opus-4-7": {
"id": "claude-opus-4-7",
"name": "Claude Opus 4.7",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-opus-4-8": {
"id": "claude-opus-4-8",
"name": "Claude Opus 4.8",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-sonnet-4-20250514": {
"id": "claude-sonnet-4-20250514",
"name": "Claude Sonnet 4",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-sonnet-4-5-20250929": {
"id": "claude-sonnet-4-5-20250929",
"name": "Claude Sonnet 4.5",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000
},
"claude-sonnet-4-6": {
"id": "claude-sonnet-4-6",
"name": "Claude Sonnet 4.6",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"command-a": {
"id": "command-a",
"name": "command-a",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"custom:happyhorse-1.0": {
"id": "custom:happyhorse-1.0",
"name": "custom:happyhorse-1.0",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"deepseek-chat": {
"id": "deepseek-chat",
"name": "DeepSeek V3/Deepseek Chat",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"deepseek-non-reasoner-v3.1-terminus": {
"id": "deepseek-non-reasoner-v3.1-terminus",
"name": "deepseek-non-reasoner-v3.1-terminus",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"deepseek-non-thinking-v3.2-exp": {
"id": "deepseek-non-thinking-v3.2-exp",
"name": "deepseek-non-thinking-v3.2-exp",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"deepseek-reasoner": {
"id": "deepseek-reasoner",
"name": "deepseek-reasoner",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"deepseek-v4-flash": {
"id": "deepseek-v4-flash",
"name": "deepseek-v4-flash",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 384000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek-v4-pro": {
"id": "deepseek-v4-pro",
"name": "deepseek-v4-pro",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 384000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek/deepseek-chat-v3-0324": {
"id": "deepseek/deepseek-chat-v3-0324",
"name": "DeepSeek V3 0324",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek/deepseek-chat-v3.1": {
"id": "deepseek/deepseek-chat-v3.1",
"name": "DeepSeek V3.1",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek/deepseek-r1": {
"id": "deepseek/deepseek-r1",
"name": "R1",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 16000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"elevenlabs/eleven_multilingual_v2": {
"id": "elevenlabs/eleven_multilingual_v2",
"name": "elevenlabs/eleven_multilingual_v2",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"elevenlabs/eleven_music": {
"id": "elevenlabs/eleven_music",
"name": "elevenlabs/eleven_music",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"elevenlabs/eleven_turbo_v2_5": {
"id": "elevenlabs/eleven_turbo_v2_5",
"name": "elevenlabs/eleven_turbo_v2_5",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"elevenlabs/v3_alpha": {
"id": "elevenlabs/v3_alpha",
"name": "elevenlabs/v3_alpha",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gc-document-ai": {
"id": "gc-document-ai",
"name": "gc-document-ai",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gemini-2.5-flash": {
"id": "gemini-2.5-flash",
"name": "Gemini 2.5 Flash",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gemini-2.5-flash-lite": {
"id": "gemini-2.5-flash-lite",
"name": "Gemini 2.5 Flash-Lite",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gemini-2.5-flash-lite-preview-09-2025": {
"id": "gemini-2.5-flash-lite-preview-09-2025",
"name": "Gemini 2.5 Flash Lite Preview (09/2025)",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gemini-2.5-pro": {
"id": "gemini-2.5-pro",
"name": "Gemini 2.5 Pro",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"gemini-3-flash-preview": {
"id": "gemini-3-flash-preview",
"name": "Gemini 3 Flash Preview",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"gemini-3.1-flash-lite": {
"id": "gemini-3.1-flash-lite",
"name": "Gemini 3.1 Flash Lite",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"gemini-3.1-flash-lite-preview": {
"id": "gemini-3.1-flash-lite-preview",
"name": "Gemini 3.1 Flash Lite Preview",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"gemini-3.1-pro-preview": {
"id": "gemini-3.1-pro-preview",
"name": "Gemini 3.1 Pro Preview",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"high"
],
"requiresEffort": true
}
},
"gemini-3.5-flash": {
"id": "gemini-3.5-flash",
"name": "Gemini 3.5 Flash",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"gemma-3-12b-it": {
"id": "gemma-3-12b-it",
"name": "gemma-3-12b-it",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384
},
"gemma-3-27b-it": {
"id": "gemma-3-27b-it",
"name": "gemma-3-27b-it",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192
},
"gemma-3-4b-it": {
"id": "gemma-3-4b-it",
"name": "gemma-3-4b-it",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gemma-3n-e4b-it": {
"id": "gemma-3n-e4b-it",
"name": "gemma-3n-e4b-it",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"gemma-4-31b-it": {
"id": "gemma-4-31b-it",
"name": "Gemma 4 31B IT",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"gen3a_turbo": {
"id": "gen3a_turbo",
"name": "gen3a_turbo",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gen4_aleph": {
"id": "gen4_aleph",
"name": "gen4_aleph",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gen4_turbo": {
"id": "gen4_turbo",
"name": "gen4_turbo",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"glm-4.5": {
"id": "glm-4.5",
"name": "glm-4.5",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 98304
},
"glm-4.5-air": {
"id": "glm-4.5-air",
"name": "GLM-4.5-Air",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 98304,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"glm-4.6": {
"id": "glm-4.6",
"name": "glm-4.6",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"glm-4.7": {
"id": "glm-4.7",
"name": "GLM-4.7",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"glm-5": {
"id": "glm-5",
"name": "GLM-5",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"glm-5.1": {
"id": "glm-5.1",
"name": "GLM-5.1",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"glm-ocr": {
"id": "glm-ocr",
"name": "glm-ocr",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gpt-3.5-turbo": {
"id": "gpt-3.5-turbo",
"name": "gpt-3.5-turbo",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 16385,
"maxTokens": 4096
},
"gpt-3.5-turbo-0125": {
"id": "gpt-3.5-turbo-0125",
"name": "gpt-3.5-turbo-0125",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gpt-3.5-turbo-0613": {
"id": "gpt-3.5-turbo-0613",
"name": "gpt-3.5-turbo-0613",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 4095,
"maxTokens": 4096
},
"gpt-3.5-turbo-1106": {
"id": "gpt-3.5-turbo-1106",
"name": "gpt-3.5-turbo-1106",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gpt-3.5-turbo-16k": {
"id": "gpt-3.5-turbo-16k",
"name": "gpt-3.5-turbo-16k",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 16385,
"maxTokens": 4096
},
"gpt-3.5-turbo-instruct": {
"id": "gpt-3.5-turbo-instruct",
"name": "gpt-3.5-turbo-instruct",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gpt-4": {
"id": "gpt-4",
"name": "GPT-4",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 8192,
"maxTokens": 8192
},
"gpt-4-0314": {
"id": "gpt-4-0314",
"name": "gpt-4-0314",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 8191,
"maxTokens": 4096
},
"gpt-4-1106-vision-preview": {
"id": "gpt-4-1106-vision-preview",
"name": "gpt-4-1106-vision-preview",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gpt-4-turbo": {
"id": "gpt-4-turbo",
"name": "GPT-4 Turbo",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"gpt-4-turbo-2024-04-09": {
"id": "gpt-4-turbo-2024-04-09",
"name": "gpt-4-turbo-2024-04-09",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gpt-4-turbo-preview": {
"id": "gpt-4-turbo-preview",
"name": "gpt-4-turbo-preview",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"gpt-4.1": {
"id": "gpt-4.1",
"name": "GPT-4.1",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1047576,
"maxTokens": 32768
},
"gpt-4.1-2025-04-14": {
"id": "gpt-4.1-2025-04-14",
"name": "gpt-4.1-2025-04-14",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gpt-4.1-mini": {
"id": "gpt-4.1-mini",
"name": "GPT-4.1 mini",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1047576,
"maxTokens": 32768
},
"gpt-4.1-mini-2025-04-14": {
"id": "gpt-4.1-mini-2025-04-14",
"name": "gpt-4.1-mini-2025-04-14",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gpt-4.1-nano": {
"id": "gpt-4.1-nano",
"name": "GPT-4.1 nano",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1047576,
"maxTokens": 32768
},
"gpt-4.1-nano-2025-04-14": {
"id": "gpt-4.1-nano-2025-04-14",
"name": "gpt-4.1-nano-2025-04-14",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gpt-4o": {
"id": "gpt-4o",
"name": "GPT-4o",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"gpt-4o-2024-05-13": {
"id": "gpt-4o-2024-05-13",
"name": "GPT-4o (2024-05-13)",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"gpt-4o-2024-08-06": {
"id": "gpt-4o-2024-08-06",
"name": "GPT-4o (2024-08-06)",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"gpt-4o-2024-11-20": {
"id": "gpt-4o-2024-11-20",
"name": "GPT-4o (2024-11-20)",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"gpt-4o-mini": {
"id": "gpt-4o-mini",
"name": "GPT-4o mini",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"gpt-4o-mini-2024-07-18": {
"id": "gpt-4o-mini-2024-07-18",
"name": "gpt-4o-mini-2024-07-18",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"gpt-4o-mini-search-preview": {
"id": "gpt-4o-mini-search-preview",
"name": "gpt-4o-mini-search-preview",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gpt-4o-mini-transcribe": {
"id": "gpt-4o-mini-transcribe",
"name": "gpt-4o-mini-transcribe",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gpt-4o-search-preview": {
"id": "gpt-4o-search-preview",
"name": "gpt-4o-search-preview",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gpt-4o-transcribe": {
"id": "gpt-4o-transcribe",
"name": "gpt-4o-transcribe",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gpt-5": {
"id": "gpt-5",
"name": "GPT-5",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5-2025-08-07": {
"id": "gpt-5-2025-08-07",
"name": "gpt-5-2025-08-07",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gpt-5-chat": {
"id": "gpt-5-chat",
"name": "gpt-5-chat",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"gpt-5-chat-latest": {
"id": "gpt-5-chat-latest",
"name": "gpt-5-chat-latest",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"gpt-5-mini": {
"id": "gpt-5-mini",
"name": "GPT-5 Mini",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5-mini-2025-08-07": {
"id": "gpt-5-mini-2025-08-07",
"name": "gpt-5-mini-2025-08-07",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"gpt-5-nano": {
"id": "gpt-5-nano",
"name": "GPT-5 Nano",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5-nano-2025-08-07": {
"id": "gpt-5-nano-2025-08-07",
"name": "gpt-5-nano-2025-08-07",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gpt-5-pro": {
"id": "gpt-5-pro",
"name": "GPT-5 Pro",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 272000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5.1-2025-11-13": {
"id": "gpt-5.1-2025-11-13",
"name": "gpt-5.1-2025-11-13",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"gpt-5.1-chat-latest": {
"id": "gpt-5.1-chat-latest",
"name": "GPT-5.1 Chat",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5.1-codex": {
"id": "gpt-5.1-codex",
"name": "GPT-5.1 Codex",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5.1-codex-mini": {
"id": "gpt-5.1-codex-mini",
"name": "GPT-5.1 Codex mini",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"medium",
"high"
]
}
},
"gpt-5.2-2025-12-11": {
"id": "gpt-5.2-2025-12-11",
"name": "gpt-5.2-2025-12-11",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gpt-5.2-chat-latest": {
"id": "gpt-5.2-chat-latest",
"name": "GPT-5.2 Chat",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.2-codex": {
"id": "gpt-5.2-codex",
"name": "GPT-5.2 Codex",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.2-pro-2025-12-11": {
"id": "gpt-5.2-pro-2025-12-11",
"name": "gpt-5.2-pro-2025-12-11",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gpt-5.3-codex": {
"id": "gpt-5.3-codex",
"name": "GPT-5.3 Codex",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.4-2026-03-05": {
"id": "gpt-5.4-2026-03-05",
"name": "gpt-5.4-2026-03-05",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gpt-5.4-pro-2026-03-05": {
"id": "gpt-5.4-pro-2026-03-05",
"name": "gpt-5.4-pro-2026-03-05",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gpt-5.5-2026-04-23": {
"id": "gpt-5.5-2026-04-23",
"name": "gpt-5.5-2026-04-23",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null,
"contextPromotionTarget": "aimlapi/gpt-5.4-2026-03-05"
},
"gpt-5.5-pro-2026-04-23": {
"id": "gpt-5.5-pro-2026-04-23",
"name": "gpt-5.5-pro-2026-04-23",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null,
"contextPromotionTarget": "aimlapi/gpt-5.4-2026-03-05"
},
"gpt-oss-120b": {
"id": "gpt-oss-120b",
"name": "GPT OSS 120B",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
]
}
},
"gpt-oss-20b": {
"id": "gpt-oss-20b",
"name": "gpt-oss-20b",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 65536
},
"grok-4-1-fast-non-reasoning": {
"id": "grok-4-1-fast-non-reasoning",
"name": "grok-4-1-fast-non-reasoning",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 30000
},
"grok-4-1-fast-reasoning": {
"id": "grok-4-1-fast-reasoning",
"name": "grok-4-1-fast-reasoning",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"grok-4-20-0309-non-reasoning": {
"id": "grok-4-20-0309-non-reasoning",
"name": "grok-4-20-0309-non-reasoning",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"grok-4-20-0309-reasoning": {
"id": "grok-4-20-0309-reasoning",
"name": "grok-4-20-0309-reasoning",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"grok-4-fast-non-reasoning": {
"id": "grok-4-fast-non-reasoning",
"name": "grok-4-fast-non-reasoning",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 30000
},
"grok-4-fast-reasoning": {
"id": "grok-4-fast-reasoning",
"name": "grok-4-fast-reasoning",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 256000
},
"happyhorse-1.0-r2v": {
"id": "happyhorse-1.0-r2v",
"name": "happyhorse-1.0-r2v",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"hermes-4-405b": {
"id": "hermes-4-405b",
"name": "hermes-4-405b",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"hunyuan-part": {
"id": "hunyuan-part",
"name": "hunyuan-part",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"klingai/avatar-pro": {
"id": "klingai/avatar-pro",
"name": "klingai/avatar-pro",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"klingai/avatar-standard": {
"id": "klingai/avatar-standard",
"name": "klingai/avatar-standard",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"ltxv-2": {
"id": "ltxv-2",
"name": "ltxv-2",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"ltxv-2/fast": {
"id": "ltxv-2/fast",
"name": "ltxv-2/fast",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"lyria2": {
"id": "lyria2",
"name": "lyria2",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"magnum-v4-72b": {
"id": "magnum-v4-72b",
"name": "magnum-v4-72b",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"meta-llama/Llama-3.3-70B-Instruct-Turbo": {
"id": "meta-llama/Llama-3.3-70B-Instruct-Turbo",
"name": "Llama 3.3 70B",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192
},
"meta-llama/llama-3.3-70b-versatile": {
"id": "meta-llama/llama-3.3-70b-versatile",
"name": "meta-llama/llama-3.3-70b-versatile",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768
},
"microsoft/mai-transcribe-1.5": {
"id": "microsoft/mai-transcribe-1.5",
"name": "microsoft/mai-transcribe-1.5",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"microsoft/mai-voice-2": {
"id": "microsoft/mai-voice-2",
"name": "microsoft/mai-voice-2",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"minimax-music": {
"id": "minimax-music",
"name": "minimax-music",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"minimax/hailuo-02": {
"id": "minimax/hailuo-02",
"name": "minimax/hailuo-02",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"minimax/hailuo-2.3": {
"id": "minimax/hailuo-2.3",
"name": "minimax/hailuo-2.3",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"minimax/hailuo-2.3-fast": {
"id": "minimax/hailuo-2.3-fast",
"name": "minimax/hailuo-2.3-fast",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"minimax/m1": {
"id": "minimax/m1",
"name": "minimax/m1",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"minimax/m2": {
"id": "minimax/m2",
"name": "minimax/m2",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"minimax/m2-1": {
"id": "minimax/m2-1",
"name": "minimax/m2-1",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"minimax/m2-1-highspeed": {
"id": "minimax/m2-1-highspeed",
"name": "minimax/m2-1-highspeed",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"minimax/m2-5-20260218": {
"id": "minimax/m2-5-20260218",
"name": "minimax/m2-5-20260218",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"minimax/m2-5-highspeed-20260218": {
"id": "minimax/m2-5-highspeed-20260218",
"name": "minimax/m2-5-highspeed-20260218",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"minimax/m2-7-20260402": {
"id": "minimax/m2-7-20260402",
"name": "minimax/m2-7-20260402",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"minimax/m2-7-highspeed": {
"id": "minimax/m2-7-highspeed",
"name": "minimax/m2-7-highspeed",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"minimax/m2-her": {
"id": "minimax/m2-her",
"name": "minimax/m2-her",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"minimax/minimax-m3": {
"id": "minimax/minimax-m3",
"name": "MiniMax-M3",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 512000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"minimax/MiniMax-Text-01": {
"id": "minimax/MiniMax-Text-01",
"name": "minimax/MiniMax-Text-01",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"minimax/music-1.5": {
"id": "minimax/music-1.5",
"name": "minimax/music-1.5",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"minimax/music-2.0": {
"id": "minimax/music-2.0",
"name": "minimax/music-2.0",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"minimax/music-2.6": {
"id": "minimax/music-2.6",
"name": "minimax/music-2.6",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"minimax/music-cover": {
"id": "minimax/music-cover",
"name": "minimax/music-cover",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"mistral-nemo": {
"id": "mistral-nemo",
"name": "Mistral Nemo",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 128000
},
"mistral-ocr-latest": {
"id": "mistral-ocr-latest",
"name": "mistral-ocr-latest",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"moonshot/kimi-k2-0905-preview": {
"id": "moonshot/kimi-k2-0905-preview",
"name": "moonshot/kimi-k2-0905-preview",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"moonshot/kimi-k2-5": {
"id": "moonshot/kimi-k2-5",
"name": "moonshot/kimi-k2-5",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536
},
"moonshot/kimi-k2-6": {
"id": "moonshot/kimi-k2-6",
"name": "moonshot/kimi-k2-6",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536
},
"moonshot/kimi-k2-preview": {
"id": "moonshot/kimi-k2-preview",
"name": "moonshot/kimi-k2-preview",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"mythomax-l2-13b": {
"id": "mythomax-l2-13b",
"name": "mythomax-l2-13b",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nano-banana": {
"id": "nano-banana",
"name": "nano-banana",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nano-banana-pro": {
"id": "nano-banana-pro",
"name": "nano-banana-pro",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nano-banana-pro-edit": {
"id": "nano-banana-pro-edit",
"name": "nano-banana-pro-edit",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nemotron-3-nano-30b-a3b": {
"id": "nemotron-3-nano-30b-a3b",
"name": "nemotron-3-nano-30b-a3b",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nemotron-3-nano-omni-30b-a3b-reasoning:free": {
"id": "nemotron-3-nano-omni-30b-a3b-reasoning:free",
"name": "nemotron-3-nano-omni-30b-a3b-reasoning:free",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nemotron-3-super-120b-a12b": {
"id": "nemotron-3-super-120b-a12b",
"name": "nemotron-3-super-120b-a12b",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nemotron-3-ultra-550b-a55b": {
"id": "nemotron-3-ultra-550b-a55b",
"name": "nemotron-3-ultra-550b-a55b",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nemotron-nano-9b-v2": {
"id": "nemotron-nano-9b-v2",
"name": "nemotron-nano-9b-v2",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nova-2-automotive": {
"id": "nova-2-automotive",
"name": "nova-2-automotive",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nova-2-conversationalai": {
"id": "nova-2-conversationalai",
"name": "nova-2-conversationalai",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nova-2-drivethru": {
"id": "nova-2-drivethru",
"name": "nova-2-drivethru",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nova-2-finance": {
"id": "nova-2-finance",
"name": "nova-2-finance",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nova-2-general": {
"id": "nova-2-general",
"name": "nova-2-general",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nova-2-medical": {
"id": "nova-2-medical",
"name": "nova-2-medical",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nova-2-meeting": {
"id": "nova-2-meeting",
"name": "nova-2-meeting",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nova-2-phonecall": {
"id": "nova-2-phonecall",
"name": "nova-2-phonecall",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nova-2-voicemail": {
"id": "nova-2-voicemail",
"name": "nova-2-voicemail",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nova-3": {
"id": "nova-3",
"name": "nova-3",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nova-3-general": {
"id": "nova-3-general",
"name": "nova-3-general",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nova-3-medical": {
"id": "nova-3-medical",
"name": "nova-3-medical",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"o1": {
"id": "o1",
"name": "o1",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"o1-2024-12-17": {
"id": "o1-2024-12-17",
"name": "o1-2024-12-17",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"o3-2025-04-16": {
"id": "o3-2025-04-16",
"name": "o3-2025-04-16",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"o3-mini": {
"id": "o3-mini",
"name": "o3-mini",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"o3-mini-2025-01-31": {
"id": "o3-mini-2025-01-31",
"name": "o3-mini-2025-01-31",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"o3-mini-high": {
"id": "o3-mini-high",
"name": "o3-mini-high",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000
},
"o3-pro": {
"id": "o3-pro",
"name": "o3-pro",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"o4-mini": {
"id": "o4-mini",
"name": "o4-mini",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"o4-mini-2025-04-16": {
"id": "o4-mini-2025-04-16",
"name": "o4-mini-2025-04-16",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"o4-mini-high": {
"id": "o4-mini-high",
"name": "o4-mini-high",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000
},
"octave-2": {
"id": "octave-2",
"name": "octave-2",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"pixverse/lip-sync": {
"id": "pixverse/lip-sync",
"name": "pixverse/lip-sync",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"pixverse/v5/transition": {
"id": "pixverse/v5/transition",
"name": "pixverse/v5/transition",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"qwen-max": {
"id": "qwen-max",
"name": "qwen-max",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"qwen-max-2025-01-25": {
"id": "qwen-max-2025-01-25",
"name": "qwen-max-2025-01-25",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"qwen-plus": {
"id": "qwen-plus",
"name": "qwen-plus",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"qwen-turbo": {
"id": "qwen-turbo",
"name": "qwen-turbo",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Qwen/Qwen2.5-7B-Instruct-Turbo": {
"id": "Qwen/Qwen2.5-7B-Instruct-Turbo",
"name": "Qwen 2.5 7B Instruct Turbo",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32768,
"maxTokens": 32768
},
"qwen3-235b-a22b-thinking-2507": {
"id": "qwen3-235b-a22b-thinking-2507",
"name": "Qwen 3 235B A22B Thinking 2507",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"qwen3-32b": {
"id": "qwen3-32b",
"name": "qwen3-32b",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 40960
},
"qwen3-coder-480b-a35b-instruct": {
"id": "qwen3-coder-480b-a35b-instruct",
"name": "qwen3-coder-480b-a35b-instruct",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 8192
},
"qwen3-max": {
"id": "qwen3-max",
"name": "qwen3-max",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536
},
"qwen3-max-preview": {
"id": "qwen3-max-preview",
"name": "qwen3-max-preview",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768
},
"qwen3-next-80b-a3b-instruct": {
"id": "qwen3-next-80b-a3b-instruct",
"name": "qwen3-next-80b-a3b-instruct",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 16384
},
"qwen3-next-80b-a3b-thinking": {
"id": "qwen3-next-80b-a3b-thinking",
"name": "qwen3-next-80b-a3b-thinking",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768
},
"qwen3-omni-30b-a3b-captioner": {
"id": "qwen3-omni-30b-a3b-captioner",
"name": "qwen3-omni-30b-a3b-captioner",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"qwen3-vl-32b-instruct": {
"id": "qwen3-vl-32b-instruct",
"name": "qwen3-vl-32b-instruct",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768
},
"qwen3-vl-32b-thinking": {
"id": "qwen3-vl-32b-thinking",
"name": "qwen3-vl-32b-thinking",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"qwen3-vl-flash": {
"id": "qwen3-vl-flash",
"name": "qwen3-vl-flash",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"qwen3-vl-plus": {
"id": "qwen3-vl-plus",
"name": "qwen3-vl-plus",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": null
},
"qwen3.5-flash": {
"id": "qwen3.5-flash",
"name": "qwen3.5-flash",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1024000,
"maxTokens": 1020000
},
"qwen3.5-omni-flash": {
"id": "qwen3.5-omni-flash",
"name": "qwen3.5-omni-flash",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"qwen3.5-omni-plus": {
"id": "qwen3.5-omni-plus",
"name": "qwen3.5-omni-plus",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"qwen3.5-plus": {
"id": "qwen3.5-plus",
"name": "Qwen3.5 Plus",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen3.6-27b": {
"id": "qwen3.6-27b",
"name": "qwen3.6-27b",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262140
},
"qwen3.6-35b-a3b": {
"id": "qwen3.6-35b-a3b",
"name": "qwen3.6-35b-a3b",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 65536
},
"qwen3.6-flash": {
"id": "qwen3.6-flash",
"name": "Qwen3.6 Flash",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen3.6-max-preview": {
"id": "qwen3.6-max-preview",
"name": "qwen3.6-max-preview",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536
},
"qwen3.6-plus": {
"id": "qwen3.6-plus",
"name": "Qwen3.6 Plus",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen3.7-max": {
"id": "qwen3.7-max",
"name": "Qwen3.7 Max",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen3.7-plus": {
"id": "qwen3.7-plus",
"name": "Qwen3.7 Plus",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"ray-2": {
"id": "ray-2",
"name": "ray-2",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"ray-flash-2": {
"id": "ray-flash-2",
"name": "ray-flash-2",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"recraft-v3": {
"id": "recraft-v3",
"name": "recraft-v3",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"redaction": {
"id": "redaction",
"name": "redaction",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"sharpen": {
"id": "sharpen",
"name": "sharpen",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"sharpen-gen": {
"id": "sharpen-gen",
"name": "sharpen-gen",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"slam-1": {
"id": "slam-1",
"name": "slam-1",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"sonar": {
"id": "sonar",
"name": "sonar",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"sonar-pro": {
"id": "sonar-pro",
"name": "sonar-pro",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"stable-diffusion-v3-medium": {
"id": "stable-diffusion-v3-medium",
"name": "stable-diffusion-v3-medium",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"stable-diffusion-v35-large": {
"id": "stable-diffusion-v35-large",
"name": "stable-diffusion-v35-large",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"stepfun/step-3.7-flash": {
"id": "stepfun/step-3.7-flash",
"name": "Step 3.7 Flash",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"triposr": {
"id": "triposr",
"name": "triposr",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"universal": {
"id": "universal",
"name": "universal",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"uso": {
"id": "uso",
"name": "uso",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"veed/fabric-1.0": {
"id": "veed/fabric-1.0",
"name": "veed/fabric-1.0",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"veed/fabric-1.0/fast": {
"id": "veed/fabric-1.0/fast",
"name": "veed/fabric-1.0/fast",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"vibevoice": {
"id": "vibevoice",
"name": "vibevoice",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"vibevoice/7b": {
"id": "vibevoice/7b",
"name": "vibevoice/7b",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"voyage-2": {
"id": "voyage-2",
"name": "voyage-2",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"voyage-code-2": {
"id": "voyage-code-2",
"name": "voyage-code-2",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"voyage-finance-2": {
"id": "voyage-finance-2",
"name": "voyage-finance-2",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"voyage-large-2": {
"id": "voyage-large-2",
"name": "voyage-large-2",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"voyage-large-2-instruct": {
"id": "voyage-large-2-instruct",
"name": "voyage-large-2-instruct",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"voyage-law-2": {
"id": "voyage-law-2",
"name": "voyage-law-2",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"voyage-multilingual-2": {
"id": "voyage-multilingual-2",
"name": "voyage-multilingual-2",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"wan2.6-r2v": {
"id": "wan2.6-r2v",
"name": "wan2.6-r2v",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"wan2.7-r2v": {
"id": "wan2.7-r2v",
"name": "wan2.7-r2v",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"x-ai/grok-3-beta": {
"id": "x-ai/grok-3-beta",
"name": "x-ai/grok-3-beta",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": null
},
"x-ai/grok-3-mini-beta": {
"id": "x-ai/grok-3-mini-beta",
"name": "x-ai/grok-3-mini-beta",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": null
},
"x-ai/grok-4-07-09": {
"id": "x-ai/grok-4-07-09",
"name": "x-ai/grok-4-07-09",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"x-ai/grok-4-3": {
"id": "x-ai/grok-4-3",
"name": "x-ai/grok-4-3",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 30000
},
"x-ai/grok-code-fast-1": {
"id": "x-ai/grok-code-fast-1",
"name": "Grok Code Fast 1",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"xai/grok-build-0-1": {
"id": "xai/grok-build-0-1",
"name": "xai/grok-build-0-1",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000
},
"xiaomi/mimo-v2-flash": {
"id": "xiaomi/mimo-v2-flash",
"name": "MiMo-V2-Flash",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"xiaomi/mimo-v2.5": {
"id": "xiaomi/mimo-v2.5",
"name": "MiMo-V2.5",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"xiaomi/mimo-v2.5-pro": {
"id": "xiaomi/mimo-v2.5-pro",
"name": "MiMo V2.5 Pro",
"api": "openai-completions",
"provider": "aimlapi",
"baseUrl": "https://api.aimlapi.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
}
},
"alibaba-coding-plan": {
"glm-4.7": {
"id": "glm-4.7",
"name": "GLM-4.7",
"api": "openai-completions",
"provider": "alibaba-coding-plan",
"baseUrl": "https://coding-intl.dashscope.aliyuncs.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 16384,
"compat": {
"supportsDeveloperRole": false
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"glm-5": {
"id": "glm-5",
"name": "GLM-5",
"api": "openai-completions",
"provider": "alibaba-coding-plan",
"baseUrl": "https://coding-intl.dashscope.aliyuncs.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 16384,
"compat": {
"supportsDeveloperRole": false
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"kimi-k2.5": {
"id": "kimi-k2.5",
"name": "Kimi K2.5",
"api": "openai-completions",
"provider": "alibaba-coding-plan",
"baseUrl": "https://coding-intl.dashscope.aliyuncs.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"compat": {
"supportsDeveloperRole": false
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"MiniMax-M2.5": {
"id": "MiniMax-M2.5",
"name": "MiniMax-M2.5",
"api": "openai-completions",
"provider": "alibaba-coding-plan",
"baseUrl": "https://coding-intl.dashscope.aliyuncs.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 196608,
"maxTokens": 24576,
"compat": {
"supportsDeveloperRole": false
},
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"qwen3-coder-next": {
"id": "qwen3-coder-next",
"name": "Qwen3 Coder Next",
"api": "openai-completions",
"provider": "alibaba-coding-plan",
"baseUrl": "https://coding-intl.dashscope.aliyuncs.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"compat": {
"supportsDeveloperRole": false
}
},
"qwen3-coder-plus": {
"id": "qwen3-coder-plus",
"name": "Qwen3 Coder Plus",
"api": "openai-completions",
"provider": "alibaba-coding-plan",
"baseUrl": "https://coding-intl.dashscope.aliyuncs.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65536,
"compat": {
"supportsDeveloperRole": false
}
},
"qwen3-max-2026-01-23": {
"id": "qwen3-max-2026-01-23",
"name": "Qwen3 Max",
"api": "openai-completions",
"provider": "alibaba-coding-plan",
"baseUrl": "https://coding-intl.dashscope.aliyuncs.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"compat": {
"supportsDeveloperRole": false
}
},
"qwen3.5-plus": {
"id": "qwen3.5-plus",
"name": "Qwen3.5 Plus",
"api": "openai-completions",
"provider": "alibaba-coding-plan",
"baseUrl": "https://coding-intl.dashscope.aliyuncs.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65536,
"compat": {
"supportsDeveloperRole": false
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen3.6-flash": {
"id": "qwen3.6-flash",
"name": "Qwen3.6 Flash",
"api": "openai-completions",
"provider": "alibaba-coding-plan",
"baseUrl": "https://coding-intl.dashscope.aliyuncs.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1875,
"output": 1.125,
"cacheRead": 0,
"cacheWrite": 0.234375
},
"contextWindow": 1000000,
"maxTokens": 65536,
"compat": {
"supportsDeveloperRole": false
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen3.6-plus": {
"id": "qwen3.6-plus",
"name": "Qwen3.6 Plus",
"api": "openai-completions",
"provider": "alibaba-coding-plan",
"baseUrl": "https://coding-intl.dashscope.aliyuncs.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65536,
"compat": {
"supportsDeveloperRole": false
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen3.7-max": {
"id": "qwen3.7-max",
"name": "Qwen3.7 Max",
"api": "openai-completions",
"provider": "alibaba-coding-plan",
"baseUrl": "https://coding-intl.dashscope.aliyuncs.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 2.5,
"output": 7.5,
"cacheRead": 0.5,
"cacheWrite": 3.125
},
"contextWindow": 1000000,
"maxTokens": 65536,
"compat": {
"supportsDeveloperRole": false
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen3.7-plus": {
"id": "qwen3.7-plus",
"name": "Qwen3.7 Plus",
"api": "openai-completions",
"provider": "alibaba-coding-plan",
"baseUrl": "https://coding-intl.dashscope.aliyuncs.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 64000,
"compat": {
"supportsDeveloperRole": false
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
}
},
"amazon-bedrock": {
"anthropic.claude-3-5-haiku-20241022-v1:0": {
"id": "anthropic.claude-3-5-haiku-20241022-v1:0",
"name": "Claude Haiku 3.5",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.8,
"output": 4,
"cacheRead": 0.08,
"cacheWrite": 1
},
"contextWindow": 200000,
"maxTokens": 8192
},
"anthropic.claude-3-5-sonnet-20240620-v1:0": {
"id": "anthropic.claude-3-5-sonnet-20240620-v1:0",
"name": "Claude Sonnet 3.5",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 8192
},
"anthropic.claude-3-5-sonnet-20241022-v2:0": {
"id": "anthropic.claude-3-5-sonnet-20241022-v2:0",
"name": "Claude Sonnet 3.5 v2",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 8192
},
"anthropic.claude-3-haiku-20240307-v1:0": {
"id": "anthropic.claude-3-haiku-20240307-v1:0",
"name": "Claude Haiku 3",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 1.25,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 4096
},
"anthropic.claude-3-opus-20240229-v1:0": {
"id": "anthropic.claude-3-opus-20240229-v1:0",
"name": "Claude Opus 3",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 75,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 4096
},
"anthropic.claude-3-sonnet-20240229-v1:0": {
"id": "anthropic.claude-3-sonnet-20240229-v1:0",
"name": "Claude Sonnet 3",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 4096
},
"anthropic.claude-opus-4-6-v1": {
"id": "anthropic.claude-opus-4-6-v1",
"name": "Claude Opus 4.6",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"xhigh": "max"
}
}
},
"anthropic.claude-opus-4-7": {
"id": "anthropic.claude-opus-4-7",
"name": "Claude Opus 4.7",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"anthropic.claude-opus-4-8": {
"id": "anthropic.claude-opus-4-8",
"name": "Claude Opus 4.8",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"au.anthropic.claude-haiku-4-5-20251001-v1:0": {
"id": "au.anthropic.claude-haiku-4-5-20251001-v1:0",
"name": "Claude Haiku 4.5 (AU)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1,
"output": 5,
"cacheRead": 0.1,
"cacheWrite": 1.25
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"au.anthropic.claude-opus-4-6-v1": {
"id": "au.anthropic.claude-opus-4-6-v1",
"name": "AU Anthropic Claude Opus 4.6",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 16.5,
"output": 82.5,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"xhigh": "max"
}
}
},
"au.anthropic.claude-opus-4-8": {
"id": "au.anthropic.claude-opus-4-8",
"name": "Claude Opus 4.8 (AU)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"au.anthropic.claude-sonnet-4-5-20250929-v1:0": {
"id": "au.anthropic.claude-sonnet-4-5-20250929-v1:0",
"name": "Claude Sonnet 4.5 (AU)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "anthropic-budget-effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"au.anthropic.claude-sonnet-4-6": {
"id": "au.anthropic.claude-sonnet-4-6",
"name": "AU Anthropic Claude Sonnet 4.6",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3.3,
"output": 16.5,
"cacheRead": 0.33,
"cacheWrite": 4.125
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-budget-effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"cohere.command-r-plus-v1:0": {
"id": "cohere.command-r-plus-v1:0",
"name": "Command R+",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"cohere.command-r-v1:0": {
"id": "cohere.command-r-v1:0",
"name": "Command R",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.5,
"output": 1.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"deepseek.v3-v1:0": {
"id": "deepseek.v3-v1:0",
"name": "DeepSeek-V3.1",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.58,
"output": 1.68,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 81920,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"deepseek.v3.2": {
"id": "deepseek.v3.2",
"name": "DeepSeek-V3.2",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.62,
"output": 1.85,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 81920,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"deepseek.v3.2-v1:0": {
"id": "deepseek.v3.2-v1:0",
"name": "DeepSeek-V3.2",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.62,
"output": 1.85,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 81920,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"eu.anthropic.claude-3-5-haiku-20241022-v1:0": {
"id": "eu.anthropic.claude-3-5-haiku-20241022-v1:0",
"name": "Claude Haiku 3.5 (EU)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.8,
"output": 4,
"cacheRead": 0.08,
"cacheWrite": 1
},
"contextWindow": 200000,
"maxTokens": 8192
},
"eu.anthropic.claude-3-5-sonnet-20240620-v1:0": {
"id": "eu.anthropic.claude-3-5-sonnet-20240620-v1:0",
"name": "Claude Sonnet 3.5 (EU)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 8192
},
"eu.anthropic.claude-3-5-sonnet-20241022-v2:0": {
"id": "eu.anthropic.claude-3-5-sonnet-20241022-v2:0",
"name": "Claude Sonnet 3.5 v2 (EU)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 8192
},
"eu.anthropic.claude-3-7-sonnet-20250219-v1:0": {
"id": "eu.anthropic.claude-3-7-sonnet-20250219-v1:0",
"name": "Claude Sonnet 3.7 (EU)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 8192
},
"eu.anthropic.claude-3-haiku-20240307-v1:0": {
"id": "eu.anthropic.claude-3-haiku-20240307-v1:0",
"name": "Claude Haiku 3 (EU)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 1.25,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 4096
},
"eu.anthropic.claude-3-opus-20240229-v1:0": {
"id": "eu.anthropic.claude-3-opus-20240229-v1:0",
"name": "Claude Opus 3 (EU)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 75,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 4096
},
"eu.anthropic.claude-3-sonnet-20240229-v1:0": {
"id": "eu.anthropic.claude-3-sonnet-20240229-v1:0",
"name": "Claude Sonnet 3 (EU)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 4096
},
"eu.anthropic.claude-fable-5": {
"id": "eu.anthropic.claude-fable-5",
"name": "Claude Fable 5 (EU)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 11,
"output": 55,
"cacheRead": 1.1,
"cacheWrite": 13.75
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"eu.anthropic.claude-haiku-4-5-20251001-v1:0": {
"id": "eu.anthropic.claude-haiku-4-5-20251001-v1:0",
"name": "Claude Haiku 4.5 (EU)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1,
"output": 5,
"cacheRead": 0.1,
"cacheWrite": 1.25
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"eu.anthropic.claude-opus-4-1-20250805-v1:0": {
"id": "eu.anthropic.claude-opus-4-1-20250805-v1:0",
"name": "Claude Opus 4.1 (EU)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 75,
"cacheRead": 1.5,
"cacheWrite": 18.75
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"eu.anthropic.claude-opus-4-20250514-v1:0": {
"id": "eu.anthropic.claude-opus-4-20250514-v1:0",
"name": "Claude Opus 4 (EU)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 75,
"cacheRead": 1.5,
"cacheWrite": 18.75
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"eu.anthropic.claude-opus-4-5-20251101-v1:0": {
"id": "eu.anthropic.claude-opus-4-5-20251101-v1:0",
"name": "Claude Opus 4.5 (EU)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "anthropic-budget-effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"eu.anthropic.claude-opus-4-6-v1": {
"id": "eu.anthropic.claude-opus-4-6-v1",
"name": "Claude Opus 4.6 (EU)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"xhigh": "max"
}
}
},
"eu.anthropic.claude-opus-4-7": {
"id": "eu.anthropic.claude-opus-4-7",
"name": "Claude Opus 4.7 (EU)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"eu.anthropic.claude-opus-4-8": {
"id": "eu.anthropic.claude-opus-4-8",
"name": "Claude Opus 4.8 (EU)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"eu.anthropic.claude-sonnet-4-20250514-v1:0": {
"id": "eu.anthropic.claude-sonnet-4-20250514-v1:0",
"name": "Claude Sonnet 4 (EU)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"eu.anthropic.claude-sonnet-4-5-20250929-v1:0": {
"id": "eu.anthropic.claude-sonnet-4-5-20250929-v1:0",
"name": "Claude Sonnet 4.5 (EU)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "anthropic-budget-effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"eu.anthropic.claude-sonnet-4-6": {
"id": "eu.anthropic.claude-sonnet-4-6",
"name": "Claude Sonnet 4.6 (EU)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3.3,
"output": 16.5,
"cacheRead": 0.33,
"cacheWrite": 4.125
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "anthropic-budget-effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"global.amazon.nova-2-lite-v1:0": {
"id": "global.amazon.nova-2-lite-v1:0",
"name": "Nova 2 Lite",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.33,
"output": 2.75,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"global.anthropic.claude-fable-5": {
"id": "global.anthropic.claude-fable-5",
"name": "Claude Fable 5 (Global)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 10,
"output": 50,
"cacheRead": 1,
"cacheWrite": 12.5
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"global.anthropic.claude-haiku-4-5-20251001-v1:0": {
"id": "global.anthropic.claude-haiku-4-5-20251001-v1:0",
"name": "Claude Haiku 4.5 (Global)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1,
"output": 5,
"cacheRead": 0.1,
"cacheWrite": 1.25
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"global.anthropic.claude-opus-4-5-20251101-v1:0": {
"id": "global.anthropic.claude-opus-4-5-20251101-v1:0",
"name": "Claude Opus 4.5",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "anthropic-budget-effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"global.anthropic.claude-opus-4-6-v1": {
"id": "global.anthropic.claude-opus-4-6-v1",
"name": "Claude Opus 4.6 (Global)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"xhigh": "max"
}
}
},
"global.anthropic.claude-opus-4-7": {
"id": "global.anthropic.claude-opus-4-7",
"name": "Claude Opus 4.7 (Global)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"global.anthropic.claude-opus-4-8": {
"id": "global.anthropic.claude-opus-4-8",
"name": "Claude Opus 4.8 (Global)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"global.anthropic.claude-sonnet-4-20250514-v1:0": {
"id": "global.anthropic.claude-sonnet-4-20250514-v1:0",
"name": "Claude Sonnet 4 (Global)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"global.anthropic.claude-sonnet-4-5-20250929-v1:0": {
"id": "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
"name": "Claude Sonnet 4.5 (Global)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "anthropic-budget-effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"global.anthropic.claude-sonnet-4-6": {
"id": "global.anthropic.claude-sonnet-4-6",
"name": "Claude Sonnet 4.6",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "anthropic-budget-effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"google.gemma-3-27b-it": {
"id": "google.gemma-3-27b-it",
"name": "Google Gemma 3 27B Instruct",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.12,
"output": 0.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 8192
},
"google.gemma-3-4b-it": {
"id": "google.gemma-3-4b-it",
"name": "Gemma 3 4B IT",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.04,
"output": 0.08,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"jp.anthropic.claude-opus-4-7": {
"id": "jp.anthropic.claude-opus-4-7",
"name": "Claude Opus 4.7 (JP)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"jp.anthropic.claude-opus-4-8": {
"id": "jp.anthropic.claude-opus-4-8",
"name": "Claude Opus 4.8 (JP)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"jp.anthropic.claude-sonnet-4-5-20250929-v1:0": {
"id": "jp.anthropic.claude-sonnet-4-5-20250929-v1:0",
"name": "Claude Sonnet 4.5 (JP)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "anthropic-budget-effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"jp.anthropic.claude-sonnet-4-6": {
"id": "jp.anthropic.claude-sonnet-4-6",
"name": "Claude Sonnet 4.6 (JP)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "anthropic-budget-effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"meta.llama3-1-405b-instruct-v1:0": {
"id": "meta.llama3-1-405b-instruct-v1:0",
"name": "Llama 3.1 405B Instruct",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 2.4,
"output": 2.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"meta.llama3-1-70b-instruct-v1:0": {
"id": "meta.llama3-1-70b-instruct-v1:0",
"name": "Llama 3.1 70B Instruct",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.72,
"output": 0.72,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"meta.llama3-1-8b-instruct-v1:0": {
"id": "meta.llama3-1-8b-instruct-v1:0",
"name": "Llama 3.1 8B Instruct",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.22,
"output": 0.22,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"minimax.minimax-m2": {
"id": "minimax.minimax-m2",
"name": "MiniMax M2",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204608,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax.minimax-m2.1": {
"id": "minimax.minimax-m2.1",
"name": "MiniMax M2.1",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax.minimax-m2.5": {
"id": "minimax.minimax-m2.5",
"name": "MiniMax M2.5",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 196608,
"maxTokens": 98304,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"mistral.devstral-2-123b": {
"id": "mistral.devstral-2-123b",
"name": "Devstral 2 123B",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.4,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 8192
},
"mistral.magistral-small-2509": {
"id": "mistral.magistral-small-2509",
"name": "Magistral Small 1.2",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.5,
"output": 1.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 40000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"mistral.ministral-3-14b-instruct": {
"id": "mistral.ministral-3-14b-instruct",
"name": "Ministral 14B 3.0",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.2,
"output": 0.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"mistral.ministral-3-3b-instruct": {
"id": "mistral.ministral-3-3b-instruct",
"name": "Ministral 3 3B",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1,
"output": 0.1,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 8192
},
"mistral.ministral-3-8b-instruct": {
"id": "mistral.ministral-3-8b-instruct",
"name": "Ministral 3 8B",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"mistral.mistral-large-2402-v1:0": {
"id": "mistral.mistral-large-2402-v1:0",
"name": "Mistral Large (24.02)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.5,
"output": 1.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"mistral.mistral-large-3-675b-instruct": {
"id": "mistral.mistral-large-3-675b-instruct",
"name": "Mistral Large 3",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.5,
"output": 1.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 8192
},
"mistral.pixtral-large-2502-v1:0": {
"id": "mistral.pixtral-large-2502-v1:0",
"name": "Pixtral Large (25.02)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"mistral.voxtral-mini-3b-2507": {
"id": "mistral.voxtral-mini-3b-2507",
"name": "Voxtral Mini 3B 2507",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.04,
"output": 0.04,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"mistral.voxtral-small-24b-2507": {
"id": "mistral.voxtral-small-24b-2507",
"name": "Voxtral Small 24B 2507",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.35,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32000,
"maxTokens": 8192
},
"moonshot.kimi-k2-thinking": {
"id": "moonshot.kimi-k2-thinking",
"name": "Kimi K2 Thinking",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262143,
"maxTokens": 16000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"moonshotai.kimi-k2.5": {
"id": "moonshotai.kimi-k2.5",
"name": "Kimi K2.5",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.6,
"output": 3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262143,
"maxTokens": 16000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"nvidia.nemotron-nano-12b-v2": {
"id": "nvidia.nemotron-nano-12b-v2",
"name": "NVIDIA Nemotron Nano 12B v2 VL BF16",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.2,
"output": 0.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"nvidia.nemotron-nano-3-30b": {
"id": "nvidia.nemotron-nano-3-30b",
"name": "NVIDIA Nemotron Nano 3 30B",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.06,
"output": 0.24,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"nvidia.nemotron-nano-9b-v2": {
"id": "nvidia.nemotron-nano-9b-v2",
"name": "NVIDIA Nemotron Nano 9B v2",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.06,
"output": 0.23,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"nvidia.nemotron-super-3-120b": {
"id": "nvidia.nemotron-super-3-120b",
"name": "NVIDIA Nemotron 3 Super 120B A12B",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.65,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai.gpt-5.4": {
"id": "openai.gpt-5.4",
"name": "GPT-5.4",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.75,
"output": 16.5,
"cacheRead": 0.275,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai.gpt-5.5": {
"id": "openai.gpt-5.5",
"name": "GPT-5.5",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5.5,
"output": 33,
"cacheRead": 0.55,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
},
"contextPromotionTarget": "amazon-bedrock/openai.gpt-5.4"
},
"openai.gpt-oss-120b": {
"id": "openai.gpt-oss-120b",
"name": "gpt-oss-120b",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai.gpt-oss-120b-1:0": {
"id": "openai.gpt-oss-120b-1:0",
"name": "gpt-oss-120b",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai.gpt-oss-20b": {
"id": "openai.gpt-oss-20b",
"name": "gpt-oss-20b",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.07,
"output": 0.3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai.gpt-oss-20b-1:0": {
"id": "openai.gpt-oss-20b-1:0",
"name": "gpt-oss-20b",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.07,
"output": 0.3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai.gpt-oss-safeguard-120b": {
"id": "openai.gpt-oss-safeguard-120b",
"name": "GPT OSS Safeguard 120B",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai.gpt-oss-safeguard-20b": {
"id": "openai.gpt-oss-safeguard-20b",
"name": "GPT OSS Safeguard 20B",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.07,
"output": 0.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"qwen.qwen3-235b-a22b-2507-v1:0": {
"id": "qwen.qwen3-235b-a22b-2507-v1:0",
"name": "Qwen3 235B A22B 2507",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.22,
"output": 0.88,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 131072
},
"qwen.qwen3-32b-v1:0": {
"id": "qwen.qwen3-32b-v1:0",
"name": "Qwen3 32B (dense)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 16384,
"maxTokens": 16384,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen.qwen3-coder-30b-a3b-v1:0": {
"id": "qwen.qwen3-coder-30b-a3b-v1:0",
"name": "Qwen3 Coder 30B A3B Instruct",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 131072
},
"qwen.qwen3-coder-480b-a35b-v1:0": {
"id": "qwen.qwen3-coder-480b-a35b-v1:0",
"name": "Qwen3 Coder 480B A35B Instruct",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.22,
"output": 1.8,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 65536
},
"qwen.qwen3-coder-next": {
"id": "qwen.qwen3-coder-next",
"name": "Qwen3 Coder Next",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.22,
"output": 1.8,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen.qwen3-next-80b-a3b": {
"id": "qwen.qwen3-next-80b-a3b",
"name": "Qwen/Qwen3-Next-80B-A3B-Instruct",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.14,
"output": 1.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262000,
"maxTokens": 262000
},
"qwen.qwen3-vl-235b-a22b": {
"id": "qwen.qwen3-vl-235b-a22b",
"name": "Qwen/Qwen3-VL-235B-A22B-Instruct",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 1.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262000,
"maxTokens": 262000
},
"us.amazon.nova-lite-v1:0": {
"id": "us.amazon.nova-lite-v1:0",
"name": "Nova Lite",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.06,
"output": 0.24,
"cacheRead": 0.015,
"cacheWrite": 0
},
"contextWindow": 300000,
"maxTokens": 8192
},
"us.amazon.nova-micro-v1:0": {
"id": "us.amazon.nova-micro-v1:0",
"name": "Nova Micro",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.035,
"output": 0.14,
"cacheRead": 0.00875,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"us.amazon.nova-premier-v1:0": {
"id": "us.amazon.nova-premier-v1:0",
"name": "Nova Premier",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 12.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 16384,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"us.amazon.nova-pro-v1:0": {
"id": "us.amazon.nova-pro-v1:0",
"name": "Nova Pro",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.8,
"output": 3.2,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 300000,
"maxTokens": 8192
},
"us.anthropic.claude-3-7-sonnet-20250219-v1:0": {
"id": "us.anthropic.claude-3-7-sonnet-20250219-v1:0",
"name": "Claude Sonnet 3.7",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 8192
},
"us.anthropic.claude-fable-5": {
"id": "us.anthropic.claude-fable-5",
"name": "Claude Fable 5 (US)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 10,
"output": 50,
"cacheRead": 1,
"cacheWrite": 12.5
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"us.anthropic.claude-haiku-4-5-20251001-v1:0": {
"id": "us.anthropic.claude-haiku-4-5-20251001-v1:0",
"name": "Claude Haiku 4.5 (US)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1,
"output": 5,
"cacheRead": 0.1,
"cacheWrite": 1.25
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"us.anthropic.claude-opus-4-1-20250805-v1:0": {
"id": "us.anthropic.claude-opus-4-1-20250805-v1:0",
"name": "Claude Opus 4.1",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 75,
"cacheRead": 1.5,
"cacheWrite": 18.75
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"us.anthropic.claude-opus-4-20250514-v1:0": {
"id": "us.anthropic.claude-opus-4-20250514-v1:0",
"name": "Claude Opus 4 (US)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 75,
"cacheRead": 1.5,
"cacheWrite": 18.75
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"us.anthropic.claude-opus-4-5-20251101-v1:0": {
"id": "us.anthropic.claude-opus-4-5-20251101-v1:0",
"name": "Claude Opus 4.5 (US)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "anthropic-budget-effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"us.anthropic.claude-opus-4-6-v1": {
"id": "us.anthropic.claude-opus-4-6-v1",
"name": "Claude Opus 4.6 (US)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"xhigh": "max"
}
}
},
"us.anthropic.claude-opus-4-7": {
"id": "us.anthropic.claude-opus-4-7",
"name": "Claude Opus 4.7 (US)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"us.anthropic.claude-opus-4-8": {
"id": "us.anthropic.claude-opus-4-8",
"name": "Claude Opus 4.8 (US)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"us.anthropic.claude-sonnet-4-20250514-v1:0": {
"id": "us.anthropic.claude-sonnet-4-20250514-v1:0",
"name": "Claude Sonnet 4 (US)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"us.anthropic.claude-sonnet-4-5-20250929-v1:0": {
"id": "us.anthropic.claude-sonnet-4-5-20250929-v1:0",
"name": "Claude Sonnet 4.5 (US)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "anthropic-budget-effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"us.anthropic.claude-sonnet-4-6": {
"id": "us.anthropic.claude-sonnet-4-6",
"name": "Claude Sonnet 4.6 (US)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "anthropic-budget-effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"us.deepseek.r1-v1:0": {
"id": "us.deepseek.r1-v1:0",
"name": "DeepSeek-R1",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.35,
"output": 5.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 32768,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"us.meta.llama3-2-11b-instruct-v1:0": {
"id": "us.meta.llama3-2-11b-instruct-v1:0",
"name": "Llama 3.2 11B Instruct",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.16,
"output": 0.16,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"us.meta.llama3-2-1b-instruct-v1:0": {
"id": "us.meta.llama3-2-1b-instruct-v1:0",
"name": "Llama 3.2 1B Instruct",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.1,
"output": 0.1,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131000,
"maxTokens": 4096
},
"us.meta.llama3-2-3b-instruct-v1:0": {
"id": "us.meta.llama3-2-3b-instruct-v1:0",
"name": "Llama 3.2 3B Instruct",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131000,
"maxTokens": 4096
},
"us.meta.llama3-2-90b-instruct-v1:0": {
"id": "us.meta.llama3-2-90b-instruct-v1:0",
"name": "Llama 3.2 90B Instruct",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.72,
"output": 0.72,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"us.meta.llama3-3-70b-instruct-v1:0": {
"id": "us.meta.llama3-3-70b-instruct-v1:0",
"name": "Llama 3.3 70B Instruct",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.72,
"output": 0.72,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"us.meta.llama4-maverick-17b-instruct-v1:0": {
"id": "us.meta.llama4-maverick-17b-instruct-v1:0",
"name": "Llama 4 Maverick 17B Instruct (US)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.24,
"output": 0.97,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 16384
},
"us.meta.llama4-scout-17b-instruct-v1:0": {
"id": "us.meta.llama4-scout-17b-instruct-v1:0",
"name": "Llama 4 Scout 17B Instruct (US)",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.17,
"output": 0.66,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 3500000,
"maxTokens": 16384
},
"writer.palmyra-x4-v1:0": {
"id": "writer.palmyra-x4-v1:0",
"name": "Palmyra X4",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 2.5,
"output": 10,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 122880,
"maxTokens": 8192,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"writer.palmyra-x5-v1:0": {
"id": "writer.palmyra-x5-v1:0",
"name": "Palmyra X5",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1040000,
"maxTokens": 8192,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"zai.glm-4.7": {
"id": "zai.glm-4.7",
"name": "GLM-4.7",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"zai.glm-4.7-flash": {
"id": "zai.glm-4.7-flash",
"name": "GLM-4.7-Flash",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.07,
"output": 0.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"zai.glm-5": {
"id": "zai.glm-5",
"name": "GLM-5",
"api": "bedrock-converse-stream",
"provider": "amazon-bedrock",
"baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 3.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 101376,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
}
},
"anthropic": {
"claude-3-5-sonnet-20240620": {
"id": "claude-3-5-sonnet-20240620",
"name": "Claude Sonnet 3.5",
"api": "anthropic-messages",
"provider": "anthropic",
"baseUrl": "https://api.anthropic.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 8192
},
"claude-3-5-sonnet-20241022": {
"id": "claude-3-5-sonnet-20241022",
"name": "Claude Sonnet 3.5 v2",
"api": "anthropic-messages",
"provider": "anthropic",
"baseUrl": "https://api.anthropic.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 8192
},
"claude-3-haiku-20240307": {
"id": "claude-3-haiku-20240307",
"name": "Claude Haiku 3",
"api": "anthropic-messages",
"provider": "anthropic",
"baseUrl": "https://api.anthropic.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 1.25,
"cacheRead": 0.03,
"cacheWrite": 0.3
},
"contextWindow": 200000,
"maxTokens": 4096
},
"claude-fable-5": {
"id": "claude-fable-5",
"name": "Claude Fable 5",
"api": "anthropic-messages",
"provider": "anthropic",
"baseUrl": "https://api.anthropic.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 10,
"output": 50,
"cacheRead": 1,
"cacheWrite": 12.5
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"low": "medium",
"medium": "high",
"high": "xhigh",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"claude-haiku-4-5": {
"id": "claude-haiku-4-5",
"name": "Claude Haiku 4.5",
"api": "anthropic-messages",
"provider": "anthropic",
"baseUrl": "https://api.anthropic.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1,
"output": 5,
"cacheRead": 0.1,
"cacheWrite": 1.25
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-haiku-4-5-20251001": {
"id": "claude-haiku-4-5-20251001",
"name": "Claude Haiku 4.5",
"api": "anthropic-messages",
"provider": "anthropic",
"baseUrl": "https://api.anthropic.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1,
"output": 5,
"cacheRead": 0.1,
"cacheWrite": 1.25
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-mythos-5": {
"id": "claude-mythos-5",
"name": "Claude Mythos 5",
"api": "anthropic-messages",
"provider": "anthropic",
"baseUrl": "https://api.anthropic.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 10,
"output": 50,
"cacheRead": 1,
"cacheWrite": 12.5
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"low": "medium",
"medium": "high",
"high": "xhigh",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"claude-opus-4-0": {
"id": "claude-opus-4-0",
"name": "Claude Opus 4",
"api": "anthropic-messages",
"provider": "anthropic",
"baseUrl": "https://api.anthropic.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 75,
"cacheRead": 1.5,
"cacheWrite": 18.75
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-opus-4-1": {
"id": "claude-opus-4-1",
"name": "Claude Opus 4.1",
"api": "anthropic-messages",
"provider": "anthropic",
"baseUrl": "https://api.anthropic.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 75,
"cacheRead": 1.5,
"cacheWrite": 18.75
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-opus-4-1-20250805": {
"id": "claude-opus-4-1-20250805",
"name": "Claude Opus 4.1",
"api": "anthropic-messages",
"provider": "anthropic",
"baseUrl": "https://api.anthropic.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 75,
"cacheRead": 1.5,
"cacheWrite": 18.75
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-opus-4-20250514": {
"id": "claude-opus-4-20250514",
"name": "Claude Opus 4",
"api": "anthropic-messages",
"provider": "anthropic",
"baseUrl": "https://api.anthropic.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 75,
"cacheRead": 1.5,
"cacheWrite": 18.75
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-opus-4-5": {
"id": "claude-opus-4-5",
"name": "Claude Opus 4.5",
"api": "anthropic-messages",
"provider": "anthropic",
"baseUrl": "https://api.anthropic.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "anthropic-budget-effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-opus-4-5-20251101": {
"id": "claude-opus-4-5-20251101",
"name": "Claude Opus 4.5",
"api": "anthropic-messages",
"provider": "anthropic",
"baseUrl": "https://api.anthropic.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "anthropic-budget-effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-opus-4-6": {
"id": "claude-opus-4-6",
"name": "Claude Opus 4.6",
"api": "anthropic-messages",
"provider": "anthropic",
"baseUrl": "https://api.anthropic.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"xhigh": "max"
}
}
},
"claude-opus-4-7": {
"id": "claude-opus-4-7",
"name": "Claude Opus 4.7",
"api": "anthropic-messages",
"provider": "anthropic",
"baseUrl": "https://api.anthropic.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"low": "medium",
"medium": "high",
"high": "xhigh",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"claude-opus-4-8": {
"id": "claude-opus-4-8",
"name": "Claude Opus 4.8",
"api": "anthropic-messages",
"provider": "anthropic",
"baseUrl": "https://api.anthropic.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"low": "medium",
"medium": "high",
"high": "xhigh",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"claude-sonnet-4-0": {
"id": "claude-sonnet-4-0",
"name": "Claude Sonnet 4",
"api": "anthropic-messages",
"provider": "anthropic",
"baseUrl": "https://api.anthropic.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-sonnet-4-20250514": {
"id": "claude-sonnet-4-20250514",
"name": "Claude Sonnet 4",
"api": "anthropic-messages",
"provider": "anthropic",
"baseUrl": "https://api.anthropic.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-sonnet-4-5": {
"id": "claude-sonnet-4-5",
"name": "Claude Sonnet 4.5",
"api": "anthropic-messages",
"provider": "anthropic",
"baseUrl": "https://api.anthropic.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "anthropic-budget-effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-sonnet-4-5-20250929": {
"id": "claude-sonnet-4-5-20250929",
"name": "Claude Sonnet 4.5",
"api": "anthropic-messages",
"provider": "anthropic",
"baseUrl": "https://api.anthropic.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "anthropic-budget-effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-sonnet-4-6": {
"id": "claude-sonnet-4-6",
"name": "Claude Sonnet 4.6",
"api": "anthropic-messages",
"provider": "anthropic",
"baseUrl": "https://api.anthropic.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortMap": {
"minimal": "low"
}
}
}
},
"azure": {
"codex-mini": {
"id": "codex-mini",
"name": "Codex Mini",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.5,
"output": 6,
"cacheRead": 0.375,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-4": {
"id": "gpt-4",
"name": "GPT-4",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 60,
"output": 120,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 8192,
"maxTokens": 8192
},
"gpt-4-32k": {
"id": "gpt-4-32k",
"name": "GPT-4 32K",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 60,
"output": 120,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32768,
"maxTokens": 32768
},
"gpt-4-turbo": {
"id": "gpt-4-turbo",
"name": "GPT-4 Turbo",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 10,
"output": 30,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"gpt-4-turbo-vision": {
"id": "gpt-4-turbo-vision",
"name": "GPT-4 Turbo Vision",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 10,
"output": 30,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"gpt-4.1": {
"id": "gpt-4.1",
"name": "GPT-4.1",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 8,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 1047576,
"maxTokens": 32768
},
"gpt-4.1-mini": {
"id": "gpt-4.1-mini",
"name": "GPT-4.1 mini",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.4,
"output": 1.6,
"cacheRead": 0.1,
"cacheWrite": 0
},
"contextWindow": 1047576,
"maxTokens": 32768
},
"gpt-4.1-nano": {
"id": "gpt-4.1-nano",
"name": "GPT-4.1 nano",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1,
"output": 0.4,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 1047576,
"maxTokens": 32768
},
"gpt-4o": {
"id": "gpt-4o",
"name": "GPT-4o",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 10,
"cacheRead": 1.25,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"gpt-4o-mini": {
"id": "gpt-4o-mini",
"name": "GPT-4o mini",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0.075,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"gpt-5": {
"id": "gpt-5",
"name": "GPT-5",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.13,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5-codex": {
"id": "gpt-5-codex",
"name": "GPT-5-Codex",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.13,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5-mini": {
"id": "gpt-5-mini",
"name": "GPT-5 Mini",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 2,
"cacheRead": 0.03,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5-nano": {
"id": "gpt-5-nano",
"name": "GPT-5 Nano",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.05,
"output": 0.4,
"cacheRead": 0.01,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5-pro": {
"id": "gpt-5-pro",
"name": "GPT-5 Pro",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 120,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 272000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5.1": {
"id": "gpt-5.1",
"name": "GPT-5.1",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5.1-chat": {
"id": "gpt-5.1-chat",
"name": "GPT-5.1 Chat",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5.1-codex": {
"id": "gpt-5.1-codex",
"name": "GPT-5.1 Codex",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5.1-codex-max": {
"id": "gpt-5.1-codex-max",
"name": "GPT-5.1 Codex Max",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5.1-codex-mini": {
"id": "gpt-5.1-codex-mini",
"name": "GPT-5.1 Codex Mini",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 2,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"medium",
"high"
]
}
},
"gpt-5.2": {
"id": "gpt-5.2",
"name": "GPT-5.2",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.2-chat": {
"id": "gpt-5.2-chat",
"name": "GPT-5.2 Chat",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.2-codex": {
"id": "gpt-5.2-codex",
"name": "GPT-5.2 Codex",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.3-chat": {
"id": "gpt-5.3-chat",
"name": "GPT-5.3 Chat",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.3-codex": {
"id": "gpt-5.3-codex",
"name": "GPT-5.3 Codex",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.4": {
"id": "gpt-5.4",
"name": "GPT-5.4",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 15,
"cacheRead": 0.25,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.4-mini": {
"id": "gpt-5.4-mini",
"name": "GPT-5.4 Mini",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.75,
"output": 4.5,
"cacheRead": 0.075,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.4-nano": {
"id": "gpt-5.4-nano",
"name": "GPT-5.4 Nano",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.2,
"output": 1.25,
"cacheRead": 0.02,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.4-pro": {
"id": "gpt-5.4-pro",
"name": "GPT-5.4 Pro",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 30,
"output": 180,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.5": {
"id": "gpt-5.5",
"name": "GPT-5.5",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 30,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
},
"contextPromotionTarget": "azure/gpt-5.4"
},
"o1": {
"id": "o1",
"name": "o1",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 60,
"cacheRead": 7.5,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"o1-mini": {
"id": "o1-mini",
"name": "o1-mini",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.1,
"output": 4.4,
"cacheRead": 0.55,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"o3": {
"id": "o3",
"name": "o3",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 8,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"o3-mini": {
"id": "o3-mini",
"name": "o3-mini",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.1,
"output": 4.4,
"cacheRead": 0.55,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"o4-mini": {
"id": "o4-mini",
"name": "o4-mini",
"api": "azure-openai-responses",
"provider": "azure",
"baseUrl": "",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.1,
"output": 4.4,
"cacheRead": 0.275,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
}
},
"cerebras": {
"gpt-oss-120b": {
"id": "gpt-oss-120b",
"name": "GPT OSS 120B",
"api": "openai-completions",
"provider": "cerebras",
"baseUrl": "https://api.cerebras.ai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.35,
"output": 0.75,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 40960,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
]
}
},
"llama3.1-8b": {
"id": "llama3.1-8b",
"name": "Llama 3.1 8B",
"api": "openai-completions",
"provider": "cerebras",
"baseUrl": "https://api.cerebras.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.1,
"output": 0.1,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32000,
"maxTokens": 8000
},
"qwen-3-235b-a22b-instruct-2507": {
"id": "qwen-3-235b-a22b-instruct-2507",
"name": "Qwen 3 235B Instruct",
"api": "openai-completions",
"provider": "cerebras",
"baseUrl": "https://api.cerebras.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 1.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131000,
"maxTokens": 32000
},
"qwen-3-coder-480b": {
"id": "qwen-3-coder-480b",
"name": "qwen-3-coder-480b",
"api": "openai-completions",
"provider": "cerebras",
"baseUrl": "https://api.cerebras.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768
},
"zai-glm-4.6": {
"id": "zai-glm-4.6",
"name": "zai-glm-4.6",
"api": "openai-completions",
"provider": "cerebras",
"baseUrl": "https://api.cerebras.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768
},
"zai-glm-4.7": {
"id": "zai-glm-4.7",
"name": "Z.AI GLM-4.7",
"api": "openai-completions",
"provider": "cerebras",
"baseUrl": "https://api.cerebras.ai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 2.25,
"output": 2.75,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 40960,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
}
},
"cloudflare-ai-gateway": {
"anthropic/claude-3-5-haiku": {
"id": "anthropic/claude-3-5-haiku",
"name": "Claude Haiku 3.5",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.8,
"output": 4,
"cacheRead": 0.08,
"cacheWrite": 1
},
"contextWindow": 200000,
"maxTokens": 8192
},
"anthropic/claude-3-haiku": {
"id": "anthropic/claude-3-haiku",
"name": "Claude Haiku 3",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 1.25,
"cacheRead": 0.03,
"cacheWrite": 0.3
},
"contextWindow": 200000,
"maxTokens": 4096
},
"anthropic/claude-3-opus": {
"id": "anthropic/claude-3-opus",
"name": "Claude Opus 3",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 75,
"cacheRead": 1.5,
"cacheWrite": 18.75
},
"contextWindow": 200000,
"maxTokens": 4096
},
"anthropic/claude-3-sonnet": {
"id": "anthropic/claude-3-sonnet",
"name": "Claude Sonnet 3",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 0.3
},
"contextWindow": 200000,
"maxTokens": 4096
},
"anthropic/claude-3.5-haiku": {
"id": "anthropic/claude-3.5-haiku",
"name": "Claude Haiku 3.5",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.8,
"output": 4,
"cacheRead": 0.08,
"cacheWrite": 1
},
"contextWindow": 200000,
"maxTokens": 8192
},
"anthropic/claude-3.5-sonnet": {
"id": "anthropic/claude-3.5-sonnet",
"name": "Claude Sonnet 3.5 v2",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 8192
},
"anthropic/claude-fable-5": {
"id": "anthropic/claude-fable-5",
"name": "Claude Fable 5",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 10,
"output": 50,
"cacheRead": 1,
"cacheWrite": 12.5
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"low": "medium",
"medium": "high",
"high": "xhigh",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"anthropic/claude-haiku-4-5": {
"id": "anthropic/claude-haiku-4-5",
"name": "Claude Haiku 4.5",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1,
"output": 5,
"cacheRead": 0.1,
"cacheWrite": 1.25
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-opus-4": {
"id": "anthropic/claude-opus-4",
"name": "Claude Opus 4",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 75,
"cacheRead": 1.5,
"cacheWrite": 18.75
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-opus-4-1": {
"id": "anthropic/claude-opus-4-1",
"name": "Claude Opus 4.1",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 75,
"cacheRead": 1.5,
"cacheWrite": 18.75
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-opus-4-5": {
"id": "anthropic/claude-opus-4-5",
"name": "Claude Opus 4.5",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "anthropic-budget-effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-opus-4-6": {
"id": "anthropic/claude-opus-4-6",
"name": "Claude Opus 4.6",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"xhigh": "max"
}
}
},
"anthropic/claude-opus-4-7": {
"id": "anthropic/claude-opus-4-7",
"name": "Claude Opus 4.7",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"low": "medium",
"medium": "high",
"high": "xhigh",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"anthropic/claude-opus-4-8": {
"id": "anthropic/claude-opus-4-8",
"name": "Claude Opus 4.8",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"low": "medium",
"medium": "high",
"high": "xhigh",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"anthropic/claude-sonnet-4": {
"id": "anthropic/claude-sonnet-4",
"name": "Claude Sonnet 4",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-sonnet-4-5": {
"id": "anthropic/claude-sonnet-4-5",
"name": "Claude Sonnet 4.5",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "anthropic-budget-effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-sonnet-4-6": {
"id": "anthropic/claude-sonnet-4-6",
"name": "Claude Sonnet 4.6",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortMap": {
"minimal": "low"
}
}
},
"claude-sonnet-4-5": {
"id": "claude-sonnet-4-5",
"name": "Claude Sonnet 4.5",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "anthropic-budget-effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-4": {
"id": "openai/gpt-4",
"name": "GPT-4",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 30,
"output": 60,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 8192,
"maxTokens": 8192
},
"openai/gpt-4-turbo": {
"id": "openai/gpt-4-turbo",
"name": "GPT-4 Turbo",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 10,
"output": 30,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"openai/gpt-4o": {
"id": "openai/gpt-4o",
"name": "GPT-4o",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 10,
"cacheRead": 1.25,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-4o-mini": {
"id": "openai/gpt-4o-mini",
"name": "GPT-4o mini",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0.08,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-5.1": {
"id": "openai/gpt-5.1",
"name": "GPT-5.1",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.13,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5.1-codex": {
"id": "openai/gpt-5.1-codex",
"name": "GPT-5.1 Codex",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5.2": {
"id": "openai/gpt-5.2",
"name": "GPT-5.2",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.2-codex": {
"id": "openai/gpt-5.2-codex",
"name": "GPT-5.2 Codex",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.3-codex": {
"id": "openai/gpt-5.3-codex",
"name": "GPT-5.3 Codex",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.4": {
"id": "openai/gpt-5.4",
"name": "GPT-5.4",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 15,
"cacheRead": 0.25,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.5": {
"id": "openai/gpt-5.5",
"name": "GPT-5.5",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 30,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
},
"contextPromotionTarget": "cloudflare-ai-gateway/openai/gpt-5.4"
},
"openai/o1": {
"id": "openai/o1",
"name": "o1",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 60,
"cacheRead": 7.5,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"openai/o3": {
"id": "openai/o3",
"name": "o3",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 8,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"openai/o3-mini": {
"id": "openai/o3-mini",
"name": "o3-mini",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.1,
"output": 4.4,
"cacheRead": 0.55,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"openai/o3-pro": {
"id": "openai/o3-pro",
"name": "o3-pro",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 20,
"output": 80,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"openai/o4-mini": {
"id": "openai/o4-mini",
"name": "o4-mini",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.1,
"output": 4.4,
"cacheRead": 0.28,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"workers-ai/@cf/moonshotai/kimi-k2.5": {
"id": "workers-ai/@cf/moonshotai/kimi-k2.5",
"name": "Kimi K2.5",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.6,
"output": 3,
"cacheRead": 0.1,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"workers-ai/@cf/moonshotai/kimi-k2.6": {
"id": "workers-ai/@cf/moonshotai/kimi-k2.6",
"name": "Kimi K2.6",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.95,
"output": 4,
"cacheRead": 0.16,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"workers-ai/@cf/nvidia/nemotron-3-120b-a12b": {
"id": "workers-ai/@cf/nvidia/nemotron-3-120b-a12b",
"name": "Nemotron 3 Super 120B",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.5,
"output": 1.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"workers-ai/@cf/zai-org/glm-4.7-flash": {
"id": "workers-ai/@cf/zai-org/glm-4.7-flash",
"name": "GLM-4.7-Flash",
"api": "anthropic-messages",
"provider": "cloudflare-ai-gateway",
"baseUrl": "https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.06,
"output": 0.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
}
},
"cursor": {
"claude-4.5-opus-high": {
"id": "claude-4.5-opus-high",
"name": "Claude 4.5 Opus",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortRouting": {
"off": "claude-4.5-opus-high",
"minimal": "claude-4.5-opus-high-thinking",
"low": "claude-4.5-opus-high-thinking",
"medium": "claude-4.5-opus-high-thinking",
"high": "claude-4.5-opus-high-thinking"
}
}
},
"claude-4.5-sonnet": {
"id": "claude-4.5-sonnet",
"name": "Claude 4.5 Sonnet",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortRouting": {
"off": "claude-4.5-sonnet",
"minimal": "claude-4.5-sonnet-thinking",
"low": "claude-4.5-sonnet-thinking",
"medium": "claude-4.5-sonnet-thinking",
"high": "claude-4.5-sonnet-thinking"
}
}
},
"claude-4.6-opus-high": {
"id": "claude-4.6-opus-high",
"name": "Claude 4.6 Opus",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortRouting": {
"off": "claude-4.6-opus-high",
"minimal": "claude-4.6-opus-high-thinking",
"low": "claude-4.6-opus-high-thinking",
"medium": "claude-4.6-opus-high-thinking",
"high": "claude-4.6-opus-high-thinking"
}
}
},
"claude-4.6-sonnet-medium": {
"id": "claude-4.6-sonnet-medium",
"name": "Claude 4.6 Sonnet",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortRouting": {
"off": "claude-4.6-sonnet-medium",
"minimal": "claude-4.6-sonnet-medium-thinking",
"low": "claude-4.6-sonnet-medium-thinking",
"medium": "claude-4.6-sonnet-medium-thinking",
"high": "claude-4.6-sonnet-medium-thinking"
}
}
},
"composer-1": {
"id": "composer-1",
"name": "Composer 1",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000
},
"composer-1.5": {
"id": "composer-1.5",
"name": "Composer 1.5",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000
},
"default": {
"id": "default",
"name": "Auto",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000
},
"gemini-3-flash": {
"id": "gemini-3-flash",
"name": "Gemini 3 Flash",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"gemini-3-pro": {
"id": "gemini-3-pro",
"name": "Gemini 3 Pro",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"high"
],
"requiresEffort": true
}
},
"gemini-3.1-pro": {
"id": "gemini-3.1-pro",
"name": "Gemini 3.1 Pro Preview",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"high"
],
"requiresEffort": true
}
},
"gpt-5.1-codex-max": {
"id": "gpt-5.1-codex-max",
"name": "GPT-5.1 Codex Max",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5.1-codex-max-high": {
"id": "gpt-5.1-codex-max-high",
"name": "GPT-5.1 Codex Max High",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5.1-codex-mini": {
"id": "gpt-5.1-codex-mini",
"name": "GPT-5.1 Codex mini",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"medium",
"high"
]
}
},
"gpt-5.1-high": {
"id": "gpt-5.1-high",
"name": "GPT-5.1 High",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000
},
"gpt-5.2": {
"id": "gpt-5.2",
"name": "GPT-5.2",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.2-codex": {
"id": "gpt-5.2-codex",
"name": "GPT-5.2 Codex",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.2-codex-fast": {
"id": "gpt-5.2-codex-fast",
"name": "GPT-5.2 Codex Fast",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 64000
},
"gpt-5.2-codex-high": {
"id": "gpt-5.2-codex-high",
"name": "GPT-5.2 Codex High",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 64000
},
"gpt-5.2-codex-high-fast": {
"id": "gpt-5.2-codex-high-fast",
"name": "GPT-5.2 Codex High Fast",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 64000
},
"gpt-5.2-codex-low": {
"id": "gpt-5.2-codex-low",
"name": "GPT-5.2 Codex Low",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 64000
},
"gpt-5.2-codex-low-fast": {
"id": "gpt-5.2-codex-low-fast",
"name": "GPT-5.2 Codex Low Fast",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 64000
},
"gpt-5.2-codex-xhigh": {
"id": "gpt-5.2-codex-xhigh",
"name": "GPT-5.2 Codex Extra High",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 64000
},
"gpt-5.2-codex-xhigh-fast": {
"id": "gpt-5.2-codex-xhigh-fast",
"name": "GPT-5.2 Codex Extra High Fast",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 64000
},
"gpt-5.2-high": {
"id": "gpt-5.2-high",
"name": "GPT-5.2 High",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.3-codex": {
"id": "gpt-5.3-codex",
"name": "GPT-5.3 Codex",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.3-codex-fast": {
"id": "gpt-5.3-codex-fast",
"name": "GPT-5.3 Codex Fast",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 64000
},
"gpt-5.3-codex-high": {
"id": "gpt-5.3-codex-high",
"name": "GPT-5.3 Codex High",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 64000
},
"gpt-5.3-codex-high-fast": {
"id": "gpt-5.3-codex-high-fast",
"name": "GPT-5.3 Codex High Fast",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 64000
},
"gpt-5.3-codex-low": {
"id": "gpt-5.3-codex-low",
"name": "GPT-5.3 Codex Low",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 64000
},
"gpt-5.3-codex-low-fast": {
"id": "gpt-5.3-codex-low-fast",
"name": "GPT-5.3 Codex Low Fast",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 64000
},
"gpt-5.3-codex-spark-preview": {
"id": "gpt-5.3-codex-spark-preview",
"name": "GPT-5.3 Codex Spark",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000
},
"gpt-5.3-codex-xhigh": {
"id": "gpt-5.3-codex-xhigh",
"name": "GPT-5.3 Codex Extra High",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 64000
},
"gpt-5.3-codex-xhigh-fast": {
"id": "gpt-5.3-codex-xhigh-fast",
"name": "GPT-5.3 Codex Extra High Fast",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 64000
},
"gpt-5.4-high": {
"id": "gpt-5.4-high",
"name": "GPT-5.4 High",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000
},
"gpt-5.4-high-fast": {
"id": "gpt-5.4-high-fast",
"name": "GPT-5.4 High Fast",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000
},
"gpt-5.4-low": {
"id": "gpt-5.4-low",
"name": "GPT-5.4 Low",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000
},
"gpt-5.4-medium": {
"id": "gpt-5.4-medium",
"name": "GPT-5.4",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000
},
"gpt-5.4-medium-fast": {
"id": "gpt-5.4-medium-fast",
"name": "GPT-5.4 Fast",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000
},
"gpt-5.4-xhigh": {
"id": "gpt-5.4-xhigh",
"name": "GPT-5.4 Extra High",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000
},
"gpt-5.4-xhigh-fast": {
"id": "gpt-5.4-xhigh-fast",
"name": "GPT-5.4 Extra High Fast",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000
},
"grok-code-fast-1": {
"id": "grok-code-fast-1",
"name": "Grok Code Fast 1",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 10000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"kimi-k2.5": {
"id": "kimi-k2.5",
"name": "Kimi K2.5",
"api": "cursor-agent",
"provider": "cursor",
"baseUrl": "https://api2.cursor.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
}
},
"deepseek": {
"deepseek-v4-flash": {
"id": "deepseek-v4-flash",
"name": "DeepSeek V4 Flash",
"api": "openai-completions",
"provider": "deepseek",
"baseUrl": "https://api.deepseek.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.14,
"output": 0.28,
"cacheRead": 0.0028,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 384000,
"compat": {
"supportsDeveloperRole": false,
"supportsReasoningEffort": true,
"maxTokensField": "max_tokens",
"supportsToolChoice": false,
"extraBody": {
"thinking": {
"type": "enabled"
}
},
"reasoningContentField": "reasoning_content",
"requiresReasoningContentForToolCalls": true,
"requiresAssistantContentForToolCalls": true
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek-v4-pro": {
"id": "deepseek-v4-pro",
"name": "DeepSeek V4 Pro",
"api": "openai-completions",
"provider": "deepseek",
"baseUrl": "https://api.deepseek.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.435,
"output": 0.87,
"cacheRead": 0.003625,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 384000,
"compat": {
"supportsDeveloperRole": false,
"supportsReasoningEffort": true,
"maxTokensField": "max_tokens",
"supportsToolChoice": false,
"extraBody": {
"thinking": {
"type": "enabled"
}
},
"reasoningContentField": "reasoning_content",
"requiresReasoningContentForToolCalls": true,
"requiresAssistantContentForToolCalls": true
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
}
},
"firepass": {
"kimi-k2.6-turbo": {
"id": "kimi-k2.6-turbo",
"name": "Kimi K2.6 Turbo (Fire Pass)",
"api": "openai-completions",
"provider": "firepass",
"baseUrl": "https://api.fireworks.ai/inference/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "none"
}
}
}
},
"fireworks": {
"deepseek-v4-flash": {
"id": "deepseek-v4-flash",
"name": "deepseek-v4-flash",
"api": "openai-completions",
"provider": "fireworks",
"baseUrl": "https://api.fireworks.ai/inference/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.14,
"output": 0.28,
"cacheRead": 0.0028,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 1048576,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
},
"compat": {
"supportsDeveloperRole": false,
"supportsReasoningEffort": true,
"maxTokensField": "max_tokens",
"supportsToolChoice": false,
"reasoningContentField": "reasoning_content",
"requiresReasoningContentForToolCalls": true,
"requiresAssistantContentForToolCalls": true
}
},
"deepseek-v4-pro": {
"id": "deepseek-v4-pro",
"name": "deepseek-v4-pro",
"api": "openai-completions",
"provider": "fireworks",
"baseUrl": "https://api.fireworks.ai/inference/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.435,
"output": 0.87,
"cacheRead": 0.003625,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 1048576,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
},
"compat": {
"supportsDeveloperRole": false,
"supportsReasoningEffort": true,
"maxTokensField": "max_tokens",
"supportsToolChoice": false,
"reasoningContentField": "reasoning_content",
"requiresReasoningContentForToolCalls": true,
"requiresAssistantContentForToolCalls": true
}
},
"flux-1-schnell-fp8": {
"id": "flux-1-schnell-fp8",
"name": "FLUX.1 [schnell] FP8",
"api": "openai-completions",
"provider": "fireworks",
"baseUrl": "https://api.fireworks.ai/inference/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null,
"supportsTools": false,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "none"
}
}
},
"glm-5": {
"id": "glm-5",
"name": "GLM-5",
"api": "openai-completions",
"provider": "fireworks",
"baseUrl": "https://api.fireworks.ai/inference/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 3.2,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "none"
}
}
},
"glm-5.1": {
"id": "glm-5.1",
"name": "GLM-5.1",
"api": "openai-completions",
"provider": "fireworks",
"baseUrl": "https://api.fireworks.ai/inference/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.4,
"output": 4.4,
"cacheRead": 0.26,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "none"
}
}
},
"glm-5.2": {
"id": "glm-5.2",
"name": "GLM-5.2",
"api": "openai-completions",
"provider": "fireworks",
"baseUrl": "https://api.fireworks.ai/inference/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "none"
}
}
},
"gpt-oss-120b": {
"id": "gpt-oss-120b",
"name": "GPT OSS 120B",
"api": "openai-completions",
"provider": "fireworks",
"baseUrl": "https://api.fireworks.ai/inference/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.35,
"output": 0.75,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 40960,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
]
}
},
"gpt-oss-20b": {
"id": "gpt-oss-20b",
"name": "OpenAI gpt-oss-20b",
"api": "openai-completions",
"provider": "fireworks",
"baseUrl": "https://api.fireworks.ai/inference/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 65536,
"supportsTools": false
},
"kimi-k2.5": {
"id": "kimi-k2.5",
"name": "Kimi K2.5",
"api": "openai-completions",
"provider": "fireworks",
"baseUrl": "https://api.fireworks.ai/inference/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.6,
"output": 3,
"cacheRead": 0.1,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "none"
}
}
},
"kimi-k2.6": {
"id": "kimi-k2.6",
"name": "Kimi K2.6",
"api": "openai-completions",
"provider": "fireworks",
"baseUrl": "https://api.fireworks.ai/inference/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.95,
"output": 4,
"cacheRead": 0.16,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "none"
}
}
},
"kimi-k2.7-code": {
"id": "kimi-k2.7-code",
"name": "Kimi K2.7 Code",
"api": "openai-completions",
"provider": "fireworks",
"baseUrl": "https://api.fireworks.ai/inference/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.95,
"output": 4,
"cacheRead": 0.19,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "none"
}
}
},
"minimax-m2.5": {
"id": "minimax-m2.5",
"name": "MiniMax M2.5",
"api": "openai-completions",
"provider": "fireworks",
"baseUrl": "https://api.fireworks.ai/inference/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.06,
"cacheWrite": 0
},
"contextWindow": 196608,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax-m2.7": {
"id": "minimax-m2.7",
"name": "MiniMax M2.7",
"api": "openai-completions",
"provider": "fireworks",
"baseUrl": "https://api.fireworks.ai/inference/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.06,
"cacheWrite": 0
},
"contextWindow": 196608,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax-m3": {
"id": "minimax-m3",
"name": "MiniMax M3 (3x usage)",
"api": "openai-completions",
"provider": "fireworks",
"baseUrl": "https://api.fireworks.ai/inference/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1,
"output": 0.4,
"cacheRead": 0.02,
"cacheWrite": 0
},
"contextWindow": 512000,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "none"
}
}
},
"nemotron-3-ultra-nvfp4": {
"id": "nemotron-3-ultra-nvfp4",
"name": "NVIDIA Nemotron 3 Ultra NVFP4",
"api": "openai-completions",
"provider": "fireworks",
"baseUrl": "https://api.fireworks.ai/inference/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "none"
}
}
},
"qwen3-embedding-8b": {
"id": "qwen3-embedding-8b",
"name": "Qwen3 Embedding 8B",
"api": "openai-completions",
"provider": "fireworks",
"baseUrl": "https://api.fireworks.ai/inference/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 40960,
"maxTokens": null,
"supportsTools": false,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortMap": {
"minimal": "none"
}
}
},
"qwen3-reranker-8b": {
"id": "qwen3-reranker-8b",
"name": "Qwen3 Reranker 8B",
"api": "openai-completions",
"provider": "fireworks",
"baseUrl": "https://api.fireworks.ai/inference/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 40960,
"maxTokens": null,
"supportsTools": false,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortMap": {
"minimal": "none"
}
}
},
"qwen3.6-plus": {
"id": "qwen3.6-plus",
"name": "Qwen3.6 Plus",
"api": "openai-completions",
"provider": "fireworks",
"baseUrl": "https://api.fireworks.ai/inference/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortMap": {
"minimal": "none"
}
},
"compat": {
"supportsDeveloperRole": false
}
},
"qwen3.7-plus": {
"id": "qwen3.7-plus",
"name": "Qwen3.7 Plus",
"api": "openai-completions",
"provider": "fireworks",
"baseUrl": "https://api.fireworks.ai/inference/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.4,
"output": 1.6,
"cacheRead": 0.04,
"cacheWrite": 0.5
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortMap": {
"minimal": "none"
}
}
}
},
"github-copilot": {
"claude-fable-5": {
"id": "claude-fable-5",
"name": "Claude Fable 5",
"api": "anthropic-messages",
"provider": "github-copilot",
"baseUrl": "https://api.githubcopilot.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 10,
"output": 50,
"cacheRead": 1,
"cacheWrite": 12.5
},
"contextWindow": 1000000,
"maxTokens": 128000,
"headers": {
"User-Agent": "opencode/1.3.15",
"X-GitHub-Api-Version": "2026-06-01"
},
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"low": "medium",
"medium": "high",
"high": "xhigh",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"claude-haiku-4.5": {
"id": "claude-haiku-4.5",
"name": "Claude Haiku 4.5",
"api": "anthropic-messages",
"provider": "github-copilot",
"baseUrl": "https://api.githubcopilot.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1,
"output": 5,
"cacheRead": 0.1,
"cacheWrite": 1.25
},
"contextWindow": 200000,
"maxTokens": 64000,
"headers": {
"User-Agent": "opencode/1.3.15",
"X-GitHub-Api-Version": "2026-06-01"
},
"premiumMultiplier": 0.33,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-opus-4.5": {
"id": "claude-opus-4.5",
"name": "Claude Opus 4.5",
"api": "anthropic-messages",
"provider": "github-copilot",
"baseUrl": "https://api.githubcopilot.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 200000,
"maxTokens": 32000,
"headers": {
"User-Agent": "opencode/1.3.15",
"X-GitHub-Api-Version": "2026-06-01"
},
"thinking": {
"mode": "anthropic-budget-effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-opus-4.6": {
"id": "claude-opus-4.6",
"name": "Claude Opus 4.6",
"api": "anthropic-messages",
"provider": "github-copilot",
"baseUrl": "https://api.githubcopilot.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 168000,
"maxTokens": 32000,
"headers": {
"User-Agent": "opencode/1.3.15",
"X-GitHub-Api-Version": "2026-06-01"
},
"premiumMultiplier": 3,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"xhigh": "max"
}
}
},
"claude-opus-4.7": {
"id": "claude-opus-4.7",
"name": "Claude Opus 4.7",
"api": "anthropic-messages",
"provider": "github-copilot",
"baseUrl": "https://api.githubcopilot.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 200000,
"maxTokens": 32000,
"headers": {
"User-Agent": "opencode/1.3.15",
"X-GitHub-Api-Version": "2026-06-01"
},
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"low": "medium",
"medium": "high",
"high": "xhigh",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"claude-opus-4.8": {
"id": "claude-opus-4.8",
"name": "Claude Opus 4.8",
"api": "anthropic-messages",
"provider": "github-copilot",
"baseUrl": "https://api.githubcopilot.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 200000,
"maxTokens": 64000,
"headers": {
"User-Agent": "opencode/1.3.15",
"X-GitHub-Api-Version": "2026-06-01"
},
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"low": "medium",
"medium": "high",
"high": "xhigh",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"claude-sonnet-4": {
"id": "claude-sonnet-4",
"name": "Claude Sonnet 4",
"api": "anthropic-messages",
"provider": "github-copilot",
"baseUrl": "https://api.githubcopilot.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 216000,
"maxTokens": 16000,
"headers": {
"User-Agent": "opencode/1.3.15",
"X-GitHub-Api-Version": "2026-06-01"
},
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-sonnet-4.5": {
"id": "claude-sonnet-4.5",
"name": "Claude Sonnet 4.5",
"api": "anthropic-messages",
"provider": "github-copilot",
"baseUrl": "https://api.githubcopilot.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 32000,
"headers": {
"User-Agent": "opencode/1.3.15",
"X-GitHub-Api-Version": "2026-06-01"
},
"thinking": {
"mode": "anthropic-budget-effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-sonnet-4.6": {
"id": "claude-sonnet-4.6",
"name": "Claude Sonnet 4.6",
"api": "anthropic-messages",
"provider": "github-copilot",
"baseUrl": "https://api.githubcopilot.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 32000,
"headers": {
"User-Agent": "opencode/1.3.15",
"X-GitHub-Api-Version": "2026-06-01"
},
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortMap": {
"minimal": "low"
}
}
},
"gemini-2.5-pro": {
"id": "gemini-2.5-pro",
"name": "Gemini 2.5 Pro",
"api": "openai-completions",
"provider": "github-copilot",
"baseUrl": "https://api.githubcopilot.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 64000,
"headers": {
"User-Agent": "opencode/1.3.15",
"X-GitHub-Api-Version": "2026-06-01"
},
"compat": {
"supportsStore": false,
"supportsDeveloperRole": false,
"supportsReasoningEffort": false
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"gemini-3-flash-preview": {
"id": "gemini-3-flash-preview",
"name": "Gemini 3 Flash Preview",
"api": "openai-completions",
"provider": "github-copilot",
"baseUrl": "https://api.githubcopilot.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.5,
"output": 3,
"cacheRead": 0.05,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 64000,
"headers": {
"User-Agent": "opencode/1.3.15",
"X-GitHub-Api-Version": "2026-06-01"
},
"compat": {
"supportsStore": false,
"supportsDeveloperRole": false,
"supportsReasoningEffort": false
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"gemini-3-pro-preview": {
"id": "gemini-3-pro-preview",
"name": "Gemini 3 Pro Preview",
"api": "openai-completions",
"provider": "github-copilot",
"baseUrl": "https://api.githubcopilot.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 64000,
"headers": {
"User-Agent": "opencode/1.3.15"
},
"compat": {
"supportsStore": false,
"supportsDeveloperRole": false,
"supportsReasoningEffort": false
},
"thinking": {
"mode": "effort",
"efforts": [
"low",
"high"
],
"requiresEffort": true
}
},
"gemini-3.1-pro-preview": {
"id": "gemini-3.1-pro-preview",
"name": "Gemini 3.1 Pro Preview",
"api": "openai-completions",
"provider": "github-copilot",
"baseUrl": "https://api.githubcopilot.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 12,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000,
"headers": {
"User-Agent": "opencode/1.3.15",
"X-GitHub-Api-Version": "2026-06-01"
},
"compat": {
"supportsStore": false,
"supportsDeveloperRole": false,
"supportsReasoningEffort": false
},
"thinking": {
"mode": "effort",
"efforts": [
"low",
"high"
],
"requiresEffort": true
}
},
"gemini-3.5-flash": {
"id": "gemini-3.5-flash",
"name": "Gemini 3.5 Flash",
"api": "openai-completions",
"provider": "github-copilot",
"baseUrl": "https://api.githubcopilot.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.5,
"output": 9,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000,
"headers": {
"User-Agent": "opencode/1.3.15",
"X-GitHub-Api-Version": "2026-06-01"
},
"compat": {
"supportsStore": false,
"supportsDeveloperRole": false,
"supportsReasoningEffort": false
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"gpt-4.1": {
"id": "gpt-4.1",
"name": "GPT-4.1",
"api": "openai-completions",
"provider": "github-copilot",
"baseUrl": "https://api.githubcopilot.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 8,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384,
"headers": {
"User-Agent": "opencode/1.3.15",
"X-GitHub-Api-Version": "2026-06-01"
},
"compat": {
"supportsStore": false,
"supportsDeveloperRole": false,
"supportsReasoningEffort": false
}
},
"gpt-4o": {
"id": "gpt-4o",
"name": "GPT-4o",
"api": "openai-completions",
"provider": "github-copilot",
"baseUrl": "https://api.githubcopilot.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096,
"headers": {
"User-Agent": "opencode/1.3.15"
},
"compat": {
"supportsStore": false,
"supportsDeveloperRole": false,
"supportsReasoningEffort": false
},
"premiumMultiplier": 0
},
"gpt-5": {
"id": "gpt-5",
"name": "GPT-5",
"api": "openai-responses",
"provider": "github-copilot",
"baseUrl": "https://api.githubcopilot.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 128000,
"headers": {
"User-Agent": "opencode/1.3.15"
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5-mini": {
"id": "gpt-5-mini",
"name": "GPT-5 Mini",
"api": "openai-responses",
"provider": "github-copilot",
"baseUrl": "https://api.githubcopilot.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 2,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 264000,
"maxTokens": 64000,
"headers": {
"User-Agent": "opencode/1.3.15",
"X-GitHub-Api-Version": "2026-06-01"
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5.1": {
"id": "gpt-5.1",
"name": "GPT-5.1",
"api": "openai-responses",
"provider": "github-copilot",
"baseUrl": "https://api.githubcopilot.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 264000,
"maxTokens": 64000,
"headers": {
"User-Agent": "opencode/1.3.15"
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5.1-codex": {
"id": "gpt-5.1-codex",
"name": "GPT-5.1 Codex",
"api": "openai-responses",
"provider": "github-copilot",
"baseUrl": "https://api.githubcopilot.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"headers": {
"User-Agent": "opencode/1.3.15"
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5.1-codex-max": {
"id": "gpt-5.1-codex-max",
"name": "GPT-5.1 Codex Max",
"api": "openai-responses",
"provider": "github-copilot",
"baseUrl": "https://api.githubcopilot.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"headers": {
"User-Agent": "opencode/1.3.15"
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5.1-codex-mini": {
"id": "gpt-5.1-codex-mini",
"name": "GPT-5.1 Codex mini",
"api": "openai-responses",
"provider": "github-copilot",
"baseUrl": "https://api.githubcopilot.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"headers": {
"User-Agent": "opencode/1.3.15"
},
"thinking": {
"mode": "effort",
"efforts": [
"medium",
"high"
]
}
},
"gpt-5.2": {
"id": "gpt-5.2",
"name": "GPT-5.2",
"api": "openai-responses",
"provider": "github-copilot",
"baseUrl": "https://api.githubcopilot.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"headers": {
"User-Agent": "opencode/1.3.15",
"X-GitHub-Api-Version": "2026-06-01"
},
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.2-codex": {
"id": "gpt-5.2-codex",
"name": "GPT-5.2 Codex",
"api": "openai-responses",
"provider": "github-copilot",
"baseUrl": "https://api.githubcopilot.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"headers": {
"User-Agent": "opencode/1.3.15",
"X-GitHub-Api-Version": "2026-06-01"
},
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.3-codex": {
"id": "gpt-5.3-codex",
"name": "GPT-5.3 Codex",
"api": "openai-responses",
"provider": "github-copilot",
"baseUrl": "https://api.githubcopilot.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"headers": {
"User-Agent": "opencode/1.3.15",
"X-GitHub-Api-Version": "2026-06-01"
},
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.4": {
"id": "gpt-5.4",
"name": "GPT-5.4",
"api": "openai-responses",
"provider": "github-copilot",
"baseUrl": "https://api.githubcopilot.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 15,
"cacheRead": 0.25,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"headers": {
"User-Agent": "opencode/1.3.15",
"X-GitHub-Api-Version": "2026-06-01"
},
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.4-mini": {
"id": "gpt-5.4-mini",
"name": "GPT-5.4 mini",
"api": "openai-responses",
"provider": "github-copilot",
"baseUrl": "https://api.githubcopilot.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.75,
"output": 4.5,
"cacheRead": 0.075,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"headers": {
"User-Agent": "opencode/1.3.15",
"X-GitHub-Api-Version": "2026-06-01"
},
"premiumMultiplier": 0.33,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.4-nano": {
"id": "gpt-5.4-nano",
"name": "GPT-5.4 nano",
"api": "openai-responses",
"provider": "github-copilot",
"baseUrl": "https://api.githubcopilot.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.2,
"output": 1.25,
"cacheRead": 0.02,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"headers": {
"User-Agent": "opencode/1.3.15",
"X-GitHub-Api-Version": "2026-06-01"
},
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.5": {
"id": "gpt-5.5",
"name": "GPT-5.5",
"api": "openai-responses",
"provider": "github-copilot",
"baseUrl": "https://api.githubcopilot.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 30,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"headers": {
"User-Agent": "opencode/1.3.15",
"X-GitHub-Api-Version": "2026-06-01"
},
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
},
"contextPromotionTarget": "github-copilot/gpt-5.4"
},
"grok-code-fast-1": {
"id": "grok-code-fast-1",
"name": "Grok Code Fast 1",
"api": "openai-completions",
"provider": "github-copilot",
"baseUrl": "https://api.githubcopilot.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 192000,
"maxTokens": 64000,
"headers": {
"User-Agent": "opencode/1.3.15"
},
"compat": {
"supportsStore": false,
"supportsDeveloperRole": false,
"supportsReasoningEffort": false
},
"premiumMultiplier": 0.25,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"raptor-mini": {
"id": "raptor-mini",
"name": "Raptor mini",
"api": "openai-completions",
"provider": "github-copilot",
"baseUrl": "https://api.githubcopilot.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 2,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"headers": {
"User-Agent": "opencode/1.3.15",
"X-GitHub-Api-Version": "2026-06-01"
},
"compat": {
"supportsStore": false,
"supportsDeveloperRole": false,
"supportsReasoningEffort": false
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
}
},
"gitlab-duo": {
"claude-haiku-4-5-20251001": {
"id": "claude-haiku-4-5-20251001",
"name": "Claude Haiku 4.5",
"api": "anthropic-messages",
"baseUrl": "https://cloud.gitlab.com/ai/v1/proxy/anthropic/",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1,
"output": 5,
"cacheRead": 0.1,
"cacheWrite": 1.25
},
"contextWindow": 200000,
"maxTokens": 64000,
"provider": "gitlab-duo",
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-opus-4-5-20251101": {
"id": "claude-opus-4-5-20251101",
"name": "Claude Opus 4.5",
"api": "anthropic-messages",
"baseUrl": "https://cloud.gitlab.com/ai/v1/proxy/anthropic/",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 75,
"cacheRead": 1.5,
"cacheWrite": 18.75
},
"contextWindow": 200000,
"maxTokens": 64000,
"provider": "gitlab-duo",
"thinking": {
"mode": "anthropic-budget-effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-sonnet-4-5-20250929": {
"id": "claude-sonnet-4-5-20250929",
"name": "Claude Sonnet 4.5",
"api": "anthropic-messages",
"baseUrl": "https://cloud.gitlab.com/ai/v1/proxy/anthropic/",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 64000,
"provider": "gitlab-duo"
},
"duo-chat-gpt-5-1": {
"id": "duo-chat-gpt-5-1",
"name": "Duo Chat GPT-5.1",
"api": "openai-completions",
"provider": "gitlab-duo",
"baseUrl": "https://cloud.gitlab.com/ai/v1/proxy/openai/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 10,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"duo-chat-gpt-5-2": {
"id": "duo-chat-gpt-5-2",
"name": "Duo Chat GPT-5.2",
"api": "openai-completions",
"provider": "gitlab-duo",
"baseUrl": "https://cloud.gitlab.com/ai/v1/proxy/openai/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"duo-chat-gpt-5-2-codex": {
"id": "duo-chat-gpt-5-2-codex",
"name": "Duo Chat GPT-5.2 Codex",
"api": "openai-responses",
"provider": "gitlab-duo",
"baseUrl": "https://cloud.gitlab.com/ai/v1/proxy/openai/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"duo-chat-gpt-5-codex": {
"id": "duo-chat-gpt-5-codex",
"name": "Duo Chat GPT-5 Codex",
"api": "openai-responses",
"provider": "gitlab-duo",
"baseUrl": "https://cloud.gitlab.com/ai/v1/proxy/openai/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 10,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"duo-chat-gpt-5-mini": {
"id": "duo-chat-gpt-5-mini",
"name": "Duo Chat GPT-5 Mini",
"api": "openai-completions",
"provider": "gitlab-duo",
"baseUrl": "https://cloud.gitlab.com/ai/v1/proxy/openai/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"duo-chat-haiku-4-5": {
"id": "duo-chat-haiku-4-5",
"name": "Duo Chat Haiku 4.5",
"api": "anthropic-messages",
"provider": "gitlab-duo",
"baseUrl": "https://cloud.gitlab.com/ai/v1/proxy/anthropic/",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1,
"output": 5,
"cacheRead": 0.1,
"cacheWrite": 1.25
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"duo-chat-opus-4-5": {
"id": "duo-chat-opus-4-5",
"name": "Duo Chat Opus 4.5",
"api": "anthropic-messages",
"provider": "gitlab-duo",
"baseUrl": "https://cloud.gitlab.com/ai/v1/proxy/anthropic/",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 75,
"cacheRead": 1.5,
"cacheWrite": 18.75
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"duo-chat-opus-4-6": {
"id": "duo-chat-opus-4-6",
"name": "Duo Chat Opus 4.6",
"api": "anthropic-messages",
"provider": "gitlab-duo",
"baseUrl": "https://cloud.gitlab.com/ai/v1/proxy/anthropic/",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"duo-chat-sonnet-4-5": {
"id": "duo-chat-sonnet-4-5",
"name": "Duo Chat Sonnet 4.5",
"api": "anthropic-messages",
"provider": "gitlab-duo",
"baseUrl": "https://cloud.gitlab.com/ai/v1/proxy/anthropic/",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"duo-chat-sonnet-4-6": {
"id": "duo-chat-sonnet-4-6",
"name": "Duo Chat Sonnet 4.6",
"api": "anthropic-messages",
"provider": "gitlab-duo",
"baseUrl": "https://cloud.gitlab.com/ai/v1/proxy/anthropic/",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5-codex": {
"id": "gpt-5-codex",
"name": "GPT-5-Codex",
"api": "openai-responses",
"baseUrl": "https://cloud.gitlab.com/ai/v1/proxy/openai/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 10,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"provider": "gitlab-duo",
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5-mini-2025-08-07": {
"id": "gpt-5-mini-2025-08-07",
"name": "GPT-5 Mini",
"api": "openai-responses",
"baseUrl": "https://cloud.gitlab.com/ai/v1/proxy/openai/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384,
"provider": "gitlab-duo",
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5.1-2025-11-13": {
"id": "gpt-5.1-2025-11-13",
"name": "GPT-5.1",
"api": "openai-responses",
"baseUrl": "https://cloud.gitlab.com/ai/v1/proxy/openai/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 10,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384,
"provider": "gitlab-duo",
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
}
},
"google": {
"gemini-1.5-flash": {
"id": "gemini-1.5-flash",
"name": "Gemini 1.5 Flash",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.075,
"output": 0.3,
"cacheRead": 0.01875,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 8192
},
"gemini-1.5-flash-8b": {
"id": "gemini-1.5-flash-8b",
"name": "Gemini 1.5 Flash-8B",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.0375,
"output": 0.15,
"cacheRead": 0.01,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 8192
},
"gemini-1.5-pro": {
"id": "gemini-1.5-pro",
"name": "Gemini 1.5 Pro",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 5,
"cacheRead": 0.3125,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 8192
},
"gemini-2.0-flash": {
"id": "gemini-2.0-flash",
"name": "Gemini 2.0 Flash",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1,
"output": 0.4,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 8192
},
"gemini-2.0-flash-lite": {
"id": "gemini-2.0-flash-lite",
"name": "Gemini 2.0 Flash-Lite",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.075,
"output": 0.3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 8192
},
"gemini-2.5-flash": {
"id": "gemini-2.5-flash",
"name": "Gemini 2.5 Flash",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 2.5,
"cacheRead": 0.03,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gemini-2.5-flash-lite": {
"id": "gemini-2.5-flash-lite",
"name": "Gemini 2.5 Flash-Lite",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1,
"output": 0.4,
"cacheRead": 0.01,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gemini-2.5-flash-lite-preview-06-17": {
"id": "gemini-2.5-flash-lite-preview-06-17",
"name": "Gemini 2.5 Flash Lite Preview 06-17",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1,
"output": 0.4,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gemini-2.5-flash-lite-preview-09-2025": {
"id": "gemini-2.5-flash-lite-preview-09-2025",
"name": "Gemini 2.5 Flash Lite Preview (09/2025)",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1,
"output": 0.4,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gemini-2.5-flash-preview-04-17": {
"id": "gemini-2.5-flash-preview-04-17",
"name": "Gemini 2.5 Flash Preview 04-17",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0.0375,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gemini-2.5-flash-preview-05-20": {
"id": "gemini-2.5-flash-preview-05-20",
"name": "Gemini 2.5 Flash Preview 05-20",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0.0375,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gemini-2.5-flash-preview-09-2025": {
"id": "gemini-2.5-flash-preview-09-2025",
"name": "Gemini 2.5 Flash Preview (09/2025)",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 2.5,
"cacheRead": 0.075,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gemini-2.5-pro": {
"id": "gemini-2.5-pro",
"name": "Gemini 2.5 Pro",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"gemini-2.5-pro-preview-05-06": {
"id": "gemini-2.5-pro-preview-05-06",
"name": "Gemini 2.5 Pro Preview 05-06",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.31,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"gemini-2.5-pro-preview-06-05": {
"id": "gemini-2.5-pro-preview-06-05",
"name": "Gemini 2.5 Pro Preview 06-05",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.31,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"gemini-3-flash-preview": {
"id": "gemini-3-flash-preview",
"name": "Gemini 3 Flash Preview",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.5,
"output": 3,
"cacheRead": 0.05,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "google-level",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"gemini-3-pro-preview": {
"id": "gemini-3-pro-preview",
"name": "Gemini 3 Pro Preview",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 12,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "google-level",
"efforts": [
"low",
"high"
],
"requiresEffort": true
}
},
"gemini-3.1-flash-lite": {
"id": "gemini-3.1-flash-lite",
"name": "Gemini 3.1 Flash Lite",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 1.5,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "google-level",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"gemini-3.1-flash-lite-preview": {
"id": "gemini-3.1-flash-lite-preview",
"name": "Gemini 3.1 Flash Lite Preview",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 1.5,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "google-level",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"gemini-3.1-pro-preview": {
"id": "gemini-3.1-pro-preview",
"name": "Gemini 3.1 Pro Preview",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 12,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "google-level",
"efforts": [
"low",
"high"
],
"requiresEffort": true
}
},
"gemini-3.1-pro-preview-customtools": {
"id": "gemini-3.1-pro-preview-customtools",
"name": "Gemini 3.1 Pro Preview Custom Tools",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 12,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "google-level",
"efforts": [
"low",
"high"
],
"requiresEffort": true
}
},
"gemini-3.5-flash": {
"id": "gemini-3.5-flash",
"name": "Gemini 3.5 Flash",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.5,
"output": 9,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "google-level",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"gemini-flash-latest": {
"id": "gemini-flash-latest",
"name": "Gemini Flash Latest",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 2.5,
"cacheRead": 0.075,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gemini-flash-lite-latest": {
"id": "gemini-flash-lite-latest",
"name": "Gemini Flash-Lite Latest",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1,
"output": 0.4,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gemini-live-2.5-flash": {
"id": "gemini-live-2.5-flash",
"name": "Gemini Live 2.5 Flash",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.5,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gemini-live-2.5-flash-preview-native-audio": {
"id": "gemini-live-2.5-flash-preview-native-audio",
"name": "Gemini Live 2.5 Flash Preview Native Audio",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.5,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gemma-3-27b-it": {
"id": "gemma-3-27b-it",
"name": "Gemma 3 27B",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192
},
"gemma-4-26b": {
"id": "gemma-4-26b",
"name": "Gemma 4 26B",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 8192,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gemma-4-26b-a4b-it": {
"id": "gemma-4-26b-a4b-it",
"name": "Gemma 4 26B A4B IT",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gemma-4-26b-it": {
"id": "gemma-4-26b-it",
"name": "Gemma 4 26B",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 8192,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gemma-4-31b": {
"id": "gemma-4-31b",
"name": "Gemma 4 31B",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 8192,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gemma-4-31b-it": {
"id": "gemma-4-31b-it",
"name": "Gemma 4 31B IT",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gemma-4-E2B-it": {
"id": "gemma-4-E2B-it",
"name": "Gemma 4 E2B IT",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gemma-4-E4B-it": {
"id": "gemma-4-E4B-it",
"name": "Gemma 4 E4B IT",
"api": "google-generative-ai",
"provider": "google",
"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
}
},
"google-antigravity": {
"claude-opus-4-5": {
"id": "claude-opus-4-5",
"name": "Claude Opus 4.5",
"api": "google-gemini-cli",
"provider": "google-antigravity",
"baseUrl": "https://daily-cloudcode-pa.googleapis.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortRouting": {
"off": "claude-opus-4-5",
"minimal": "claude-opus-4-5-thinking",
"low": "claude-opus-4-5-thinking",
"medium": "claude-opus-4-5-thinking",
"high": "claude-opus-4-5-thinking"
}
},
"requestModelId": "claude-opus-4-5-thinking"
},
"claude-opus-4-6": {
"id": "claude-opus-4-6",
"name": "Claude Opus 4.6",
"api": "google-gemini-cli",
"provider": "google-antigravity",
"baseUrl": "https://daily-cloudcode-pa.googleapis.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortRouting": {
"off": "claude-opus-4-6",
"minimal": "claude-opus-4-6-thinking",
"low": "claude-opus-4-6-thinking",
"medium": "claude-opus-4-6-thinking",
"high": "claude-opus-4-6-thinking"
}
},
"requestModelId": "claude-opus-4-6-thinking"
},
"claude-sonnet-4-5": {
"id": "claude-sonnet-4-5",
"name": "Claude Sonnet 4.5",
"api": "google-gemini-cli",
"provider": "google-antigravity",
"baseUrl": "https://daily-cloudcode-pa.googleapis.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortRouting": {
"off": "claude-sonnet-4-5",
"minimal": "claude-sonnet-4-5-thinking",
"low": "claude-sonnet-4-5-thinking",
"medium": "claude-sonnet-4-5-thinking",
"high": "claude-sonnet-4-5-thinking"
}
},
"requestModelId": "claude-sonnet-4-5"
},
"claude-sonnet-4-6": {
"id": "claude-sonnet-4-6",
"name": "Claude Sonnet 4.6",
"api": "google-gemini-cli",
"provider": "google-antigravity",
"baseUrl": "https://daily-cloudcode-pa.googleapis.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortRouting": {
"off": "claude-sonnet-4-6",
"minimal": "claude-sonnet-4-6-thinking",
"low": "claude-sonnet-4-6-thinking",
"medium": "claude-sonnet-4-6-thinking",
"high": "claude-sonnet-4-6-thinking"
}
},
"requestModelId": "claude-sonnet-4-6"
},
"gemini-2.5-flash": {
"id": "gemini-2.5-flash",
"name": "Gemini 2.5 Flash",
"api": "google-gemini-cli",
"provider": "google-antigravity",
"baseUrl": "https://daily-cloudcode-pa.googleapis.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortRouting": {
"off": "gemini-2.5-flash",
"minimal": "gemini-2.5-flash-thinking",
"low": "gemini-2.5-flash-thinking",
"medium": "gemini-2.5-flash-thinking",
"high": "gemini-2.5-flash-thinking"
}
}
},
"gemini-2.5-pro": {
"id": "gemini-2.5-pro",
"name": "Gemini 2.5 Pro",
"api": "google-gemini-cli",
"provider": "google-antigravity",
"baseUrl": "https://daily-cloudcode-pa.googleapis.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"gemini-3-flash": {
"id": "gemini-3-flash",
"name": "Gemini 3 Flash",
"api": "google-gemini-cli",
"provider": "google-antigravity",
"baseUrl": "https://daily-cloudcode-pa.googleapis.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortBudgets": {
"minimal": 1000,
"low": 1000,
"medium": 4000,
"high": 10000
},
"effortRouting": {
"off": "gemini-3.5-flash-extra-low",
"minimal": "gemini-3.5-flash-extra-low",
"low": "gemini-3.5-flash-extra-low",
"medium": "gemini-3.5-flash-low",
"high": "gemini-3-flash-agent"
},
"suppressWhenOff": true
},
"requestModelId": "gemini-3.5-flash-extra-low"
},
"gemini-3-pro": {
"id": "gemini-3-pro",
"name": "Gemini 3 Pro",
"api": "google-gemini-cli",
"provider": "google-antigravity",
"baseUrl": "https://daily-cloudcode-pa.googleapis.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65535,
"thinking": {
"mode": "google-level",
"efforts": [
"low",
"high"
],
"effortRouting": {
"off": "gemini-3-pro-low",
"low": "gemini-3-pro-low",
"high": "gemini-3-pro-high"
},
"suppressWhenOff": true
},
"requestModelId": "gemini-3-pro-low"
},
"gemini-3.1-pro": {
"id": "gemini-3.1-pro",
"name": "Gemini 3.1 Pro Preview",
"api": "google-gemini-cli",
"provider": "google-antigravity",
"baseUrl": "https://daily-cloudcode-pa.googleapis.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65535,
"thinking": {
"mode": "budget",
"efforts": [
"low",
"high"
],
"effortBudgets": {
"low": 1001,
"high": 10001
},
"effortRouting": {
"off": "gemini-3.1-pro-low",
"low": "gemini-3.1-pro-low",
"high": "gemini-pro-agent"
},
"suppressWhenOff": true
},
"requestModelId": "gemini-3.1-pro-low"
},
"gpt-oss-120b": {
"id": "gpt-oss-120b",
"name": "GPT OSS 120B",
"api": "google-gemini-cli",
"provider": "google-antigravity",
"baseUrl": "https://daily-cloudcode-pa.googleapis.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 114000,
"maxTokens": 32768,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
},
"requestModelId": "gpt-oss-120b-medium"
}
},
"google-gemini-cli": {
"gemini-2.0-flash": {
"id": "gemini-2.0-flash",
"name": "Gemini 2.0 Flash",
"api": "google-gemini-cli",
"provider": "google-gemini-cli",
"baseUrl": "https://cloudcode-pa.googleapis.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 8192
},
"gemini-2.5-flash": {
"id": "gemini-2.5-flash",
"name": "Gemini 2.5 Flash",
"api": "google-gemini-cli",
"provider": "google-gemini-cli",
"baseUrl": "https://cloudcode-pa.googleapis.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortRouting": {
"off": "gemini-2.5-flash",
"minimal": "gemini-2.5-flash-thinking",
"low": "gemini-2.5-flash-thinking",
"medium": "gemini-2.5-flash-thinking",
"high": "gemini-2.5-flash-thinking"
}
}
},
"gemini-2.5-pro": {
"id": "gemini-2.5-pro",
"name": "Gemini 2.5 Pro",
"api": "google-gemini-cli",
"provider": "google-gemini-cli",
"baseUrl": "https://cloudcode-pa.googleapis.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"gemini-3-flash-preview": {
"id": "gemini-3-flash-preview",
"name": "Gemini 3 Flash Preview",
"api": "google-gemini-cli",
"provider": "google-gemini-cli",
"baseUrl": "https://cloudcode-pa.googleapis.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "google-level",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"gemini-3-pro-preview": {
"id": "gemini-3-pro-preview",
"name": "Gemini 3 Pro Preview",
"api": "google-gemini-cli",
"provider": "google-gemini-cli",
"baseUrl": "https://cloudcode-pa.googleapis.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "google-level",
"efforts": [
"low",
"high"
],
"requiresEffort": true
}
},
"gemini-3.1-flash-lite-preview": {
"id": "gemini-3.1-flash-lite-preview",
"name": "Gemini 3.1 Flash Lite Preview",
"api": "google-gemini-cli",
"provider": "google-gemini-cli",
"baseUrl": "https://cloudcode-pa.googleapis.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "google-level",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"gemini-3.1-pro-preview": {
"id": "gemini-3.1-pro-preview",
"name": "Gemini 3.1 Pro Preview",
"api": "google-gemini-cli",
"provider": "google-gemini-cli",
"baseUrl": "https://cloudcode-pa.googleapis.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "google-level",
"efforts": [
"low",
"high"
],
"requiresEffort": true
}
}
},
"google-vertex": {
"claude-haiku-4-5@20251001": {
"id": "claude-haiku-4-5@20251001",
"name": "Claude Haiku 4.5",
"api": "anthropic-messages",
"provider": "google-vertex",
"baseUrl": "https://{location}-aiplatform.googleapis.com/v1/projects/{project}/locations/{location}/publishers/anthropic/models/claude-haiku-4-5@20251001:streamRawPredict",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1,
"output": 5,
"cacheRead": 0.1,
"cacheWrite": 1.25
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-opus-4-5@20251101": {
"id": "claude-opus-4-5@20251101",
"name": "Claude Opus 4.5",
"api": "anthropic-messages",
"provider": "google-vertex",
"baseUrl": "https://{location}-aiplatform.googleapis.com/v1/projects/{project}/locations/{location}/publishers/anthropic/models/claude-opus-4-5@20251101:streamRawPredict",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "anthropic-budget-effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-opus-4-6@default": {
"id": "claude-opus-4-6@default",
"name": "Claude Opus 4.6",
"api": "anthropic-messages",
"provider": "google-vertex",
"baseUrl": "https://{location}-aiplatform.googleapis.com/v1/projects/{project}/locations/{location}/publishers/anthropic/models/claude-opus-4-6@default:streamRawPredict",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"xhigh": "max"
}
}
},
"claude-opus-4-7@default": {
"id": "claude-opus-4-7@default",
"name": "Claude Opus 4.7",
"api": "anthropic-messages",
"provider": "google-vertex",
"baseUrl": "https://{location}-aiplatform.googleapis.com/v1/projects/{project}/locations/{location}/publishers/anthropic/models/claude-opus-4-7@default:streamRawPredict",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"low": "medium",
"medium": "high",
"high": "xhigh",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"claude-opus-4-8@default": {
"id": "claude-opus-4-8@default",
"name": "Claude Opus 4.8",
"api": "anthropic-messages",
"provider": "google-vertex",
"baseUrl": "https://{location}-aiplatform.googleapis.com/v1/projects/{project}/locations/{location}/publishers/anthropic/models/claude-opus-4-8@default:streamRawPredict",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"low": "medium",
"medium": "high",
"high": "xhigh",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"claude-sonnet-4-5@20250929": {
"id": "claude-sonnet-4-5@20250929",
"name": "Claude Sonnet 4.5",
"api": "anthropic-messages",
"provider": "google-vertex",
"baseUrl": "https://{location}-aiplatform.googleapis.com/v1/projects/{project}/locations/{location}/publishers/anthropic/models/claude-sonnet-4-5@20250929:streamRawPredict",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "anthropic-budget-effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-sonnet-4-6@default": {
"id": "claude-sonnet-4-6@default",
"name": "Claude Sonnet 4.6",
"api": "anthropic-messages",
"provider": "google-vertex",
"baseUrl": "https://{location}-aiplatform.googleapis.com/v1/projects/{project}/locations/{location}/publishers/anthropic/models/claude-sonnet-4-6@default:streamRawPredict",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortMap": {
"minimal": "low"
}
}
},
"deepseek-ai/deepseek-v3.1-maas": {
"id": "deepseek-ai/deepseek-v3.1-maas",
"name": "DeepSeek V3.1",
"api": "openai-completions",
"provider": "google-vertex",
"baseUrl": "https://{location}-aiplatform.googleapis.com/v1/projects/{project}/locations/{location}/endpoints/openapi",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 1.7,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek-ai/deepseek-v3.2-maas": {
"id": "deepseek-ai/deepseek-v3.2-maas",
"name": "DeepSeek V3.2",
"api": "openai-completions",
"provider": "google-vertex",
"baseUrl": "https://{location}-aiplatform.googleapis.com/v1/projects/{project}/locations/{location}/endpoints/openapi",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.56,
"output": 1.68,
"cacheRead": 0.056,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"gemini-2.5-flash": {
"id": "gemini-2.5-flash",
"name": "Gemini 2.5 Flash",
"api": "google-vertex",
"provider": "google-vertex",
"baseUrl": "https://{location}-aiplatform.googleapis.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 2.5,
"cacheRead": 0.075,
"cacheWrite": 0.383
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gemini-2.5-flash-lite": {
"id": "gemini-2.5-flash-lite",
"name": "Gemini 2.5 Flash-Lite",
"api": "google-vertex",
"provider": "google-vertex",
"baseUrl": "https://{location}-aiplatform.googleapis.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1,
"output": 0.4,
"cacheRead": 0.01,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gemini-2.5-pro": {
"id": "gemini-2.5-pro",
"name": "Gemini 2.5 Pro",
"api": "google-vertex",
"provider": "google-vertex",
"baseUrl": "https://{location}-aiplatform.googleapis.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"gemini-3-flash-preview": {
"id": "gemini-3-flash-preview",
"name": "Gemini 3 Flash Preview",
"api": "google-vertex",
"provider": "google-vertex",
"baseUrl": "https://{location}-aiplatform.googleapis.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.5,
"output": 3,
"cacheRead": 0.05,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "google-level",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"gemini-3.1-flash-lite": {
"id": "gemini-3.1-flash-lite",
"name": "Gemini 3.1 Flash Lite",
"api": "google-vertex",
"provider": "google-vertex",
"baseUrl": "https://{location}-aiplatform.googleapis.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 1.5,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "google-level",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"gemini-3.1-flash-lite-preview": {
"id": "gemini-3.1-flash-lite-preview",
"name": "Gemini 3.1 Flash Lite Preview",
"api": "google-vertex",
"provider": "google-vertex",
"baseUrl": "https://{location}-aiplatform.googleapis.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 1.5,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "google-level",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"gemini-3.1-pro-preview": {
"id": "gemini-3.1-pro-preview",
"name": "Gemini 3.1 Pro Preview",
"api": "google-vertex",
"provider": "google-vertex",
"baseUrl": "https://{location}-aiplatform.googleapis.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 12,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "google-level",
"efforts": [
"low",
"high"
],
"requiresEffort": true
}
},
"gemini-3.1-pro-preview-customtools": {
"id": "gemini-3.1-pro-preview-customtools",
"name": "Gemini 3.1 Pro Preview Custom Tools",
"api": "google-vertex",
"provider": "google-vertex",
"baseUrl": "https://{location}-aiplatform.googleapis.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 12,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "google-level",
"efforts": [
"low",
"high"
],
"requiresEffort": true
}
},
"gemini-3.5-flash": {
"id": "gemini-3.5-flash",
"name": "Gemini 3.5 Flash",
"api": "google-vertex",
"provider": "google-vertex",
"baseUrl": "https://{location}-aiplatform.googleapis.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.5,
"output": 9,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "google-level",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"gemini-flash-latest": {
"id": "gemini-flash-latest",
"name": "Gemini Flash Latest",
"api": "google-vertex",
"provider": "google-vertex",
"baseUrl": "https://{location}-aiplatform.googleapis.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 2.5,
"cacheRead": 0.075,
"cacheWrite": 0.383
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gemini-flash-lite-latest": {
"id": "gemini-flash-lite-latest",
"name": "Gemini Flash-Lite Latest",
"api": "google-vertex",
"provider": "google-vertex",
"baseUrl": "https://{location}-aiplatform.googleapis.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1,
"output": 0.4,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"meta/llama-3.3-70b-instruct-maas": {
"id": "meta/llama-3.3-70b-instruct-maas",
"name": "Llama 3.3 70B Instruct",
"api": "openai-completions",
"provider": "google-vertex",
"baseUrl": "https://{location}-aiplatform.googleapis.com/v1/projects/{project}/locations/{location}/endpoints/openapi",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.72,
"output": 0.72,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"meta/llama-4-maverick-17b-128e-instruct-maas": {
"id": "meta/llama-4-maverick-17b-128e-instruct-maas",
"name": "Llama 4 Maverick 17B 128E Instruct",
"api": "openai-completions",
"provider": "google-vertex",
"baseUrl": "https://{location}-aiplatform.googleapis.com/v1/projects/{project}/locations/{location}/endpoints/openapi",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.35,
"output": 1.15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 524288,
"maxTokens": 8192
},
"moonshotai/kimi-k2-thinking-maas": {
"id": "moonshotai/kimi-k2-thinking-maas",
"name": "Kimi K2 Thinking",
"api": "openai-completions",
"provider": "google-vertex",
"baseUrl": "https://{location}-aiplatform.googleapis.com/v1/projects/{project}/locations/{location}/endpoints/openapi",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"openai/gpt-oss-120b-maas": {
"id": "openai/gpt-oss-120b-maas",
"name": "GPT OSS 120B",
"api": "openai-completions",
"provider": "google-vertex",
"baseUrl": "https://{location}-aiplatform.googleapis.com/v1/projects/{project}/locations/{location}/endpoints/openapi",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.09,
"output": 0.36,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
]
}
},
"openai/gpt-oss-20b-maas": {
"id": "openai/gpt-oss-20b-maas",
"name": "GPT OSS 20B",
"api": "openai-completions",
"provider": "google-vertex",
"baseUrl": "https://{location}-aiplatform.googleapis.com/v1/projects/{project}/locations/{location}/endpoints/openapi",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.07,
"output": 0.25,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
]
}
},
"qwen/qwen3-235b-a22b-instruct-2507-maas": {
"id": "qwen/qwen3-235b-a22b-instruct-2507-maas",
"name": "Qwen3 235B A22B Instruct",
"api": "openai-completions",
"provider": "google-vertex",
"baseUrl": "https://{location}-aiplatform.googleapis.com/v1/projects/{project}/locations/{location}/endpoints/openapi",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.22,
"output": 0.88,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"zai-org/glm-4.7-maas": {
"id": "zai-org/glm-4.7-maas",
"name": "GLM-4.7",
"api": "openai-completions",
"provider": "google-vertex",
"baseUrl": "https://{location}-aiplatform.googleapis.com/v1/projects/{project}/locations/{location}/endpoints/openapi",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai-org/glm-5-maas": {
"id": "zai-org/glm-5-maas",
"name": "GLM-5",
"api": "openai-completions",
"provider": "google-vertex",
"baseUrl": "https://{location}-aiplatform.googleapis.com/v1/projects/{project}/locations/{location}/endpoints/openapi",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 3.2,
"cacheRead": 0.1,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
}
},
"groq": {
"deepseek-r1-distill-llama-70b": {
"id": "deepseek-r1-distill-llama-70b",
"name": "DeepSeek R1 Distill Llama 70B",
"api": "openai-completions",
"provider": "groq",
"baseUrl": "https://api.groq.com/openai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.75,
"output": 0.99,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"gemma2-9b-it": {
"id": "gemma2-9b-it",
"name": "Gemma 2 9B",
"api": "openai-completions",
"provider": "groq",
"baseUrl": "https://api.groq.com/openai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.2,
"output": 0.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 8192,
"maxTokens": 8192
},
"groq/compound": {
"id": "groq/compound",
"name": "Compound",
"api": "openai-completions",
"provider": "groq",
"baseUrl": "https://api.groq.com/openai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"groq/compound-mini": {
"id": "groq/compound-mini",
"name": "Compound Mini",
"api": "openai-completions",
"provider": "groq",
"baseUrl": "https://api.groq.com/openai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"llama-3.1-8b-instant": {
"id": "llama-3.1-8b-instant",
"name": "Llama 3.1 8B",
"api": "openai-completions",
"provider": "groq",
"baseUrl": "https://api.groq.com/openai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.05,
"output": 0.08,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072
},
"llama-3.3-70b-versatile": {
"id": "llama-3.3-70b-versatile",
"name": "Llama 3.3 70B",
"api": "openai-completions",
"provider": "groq",
"baseUrl": "https://api.groq.com/openai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.59,
"output": 0.79,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768
},
"llama3-70b-8192": {
"id": "llama3-70b-8192",
"name": "Llama 3 70B",
"api": "openai-completions",
"provider": "groq",
"baseUrl": "https://api.groq.com/openai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.59,
"output": 0.79,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 8192,
"maxTokens": 8192
},
"llama3-8b-8192": {
"id": "llama3-8b-8192",
"name": "Llama 3 8B",
"api": "openai-completions",
"provider": "groq",
"baseUrl": "https://api.groq.com/openai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.05,
"output": 0.08,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 8192,
"maxTokens": 8192
},
"meta-llama/llama-4-maverick-17b-128e-instruct": {
"id": "meta-llama/llama-4-maverick-17b-128e-instruct",
"name": "Llama 4 Maverick 17B",
"api": "openai-completions",
"provider": "groq",
"baseUrl": "https://api.groq.com/openai/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.2,
"output": 0.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192
},
"meta-llama/llama-4-scout-17b-16e-instruct": {
"id": "meta-llama/llama-4-scout-17b-16e-instruct",
"name": "Llama 4 Scout 17B 16E",
"api": "openai-completions",
"provider": "groq",
"baseUrl": "https://api.groq.com/openai/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.11,
"output": 0.34,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192
},
"mistral-saba-24b": {
"id": "mistral-saba-24b",
"name": "Mistral Saba 24B",
"api": "openai-completions",
"provider": "groq",
"baseUrl": "https://api.groq.com/openai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.79,
"output": 0.79,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32768,
"maxTokens": 32768
},
"moonshotai/kimi-k2-instruct": {
"id": "moonshotai/kimi-k2-instruct",
"name": "Kimi K2 Instruct",
"api": "openai-completions",
"provider": "groq",
"baseUrl": "https://api.groq.com/openai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384
},
"moonshotai/kimi-k2-instruct-0905": {
"id": "moonshotai/kimi-k2-instruct-0905",
"name": "Kimi K2 0905",
"api": "openai-completions",
"provider": "groq",
"baseUrl": "https://api.groq.com/openai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 3,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 16384
},
"openai/gpt-oss-120b": {
"id": "openai/gpt-oss-120b",
"name": "GPT OSS 120B",
"api": "openai-completions",
"provider": "groq",
"baseUrl": "https://api.groq.com/openai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0.075,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
]
}
},
"openai/gpt-oss-20b": {
"id": "openai/gpt-oss-20b",
"name": "GPT OSS 20B",
"api": "openai-completions",
"provider": "groq",
"baseUrl": "https://api.groq.com/openai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.075,
"output": 0.3,
"cacheRead": 0.0375,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
]
}
},
"openai/gpt-oss-safeguard-20b": {
"id": "openai/gpt-oss-safeguard-20b",
"name": "Safety GPT OSS 20B",
"api": "openai-completions",
"provider": "groq",
"baseUrl": "https://api.groq.com/openai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.075,
"output": 0.3,
"cacheRead": 0.037,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
]
}
},
"qwen-qwq-32b": {
"id": "qwen-qwq-32b",
"name": "Qwen QwQ 32B",
"api": "openai-completions",
"provider": "groq",
"baseUrl": "https://api.groq.com/openai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.29,
"output": 0.39,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3-32b": {
"id": "qwen/qwen3-32b",
"name": "Qwen3-32B",
"api": "openai-completions",
"provider": "groq",
"baseUrl": "https://api.groq.com/openai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.29,
"output": 0.59,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 40960,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortMap": {
"minimal": "default",
"low": "default",
"medium": "default",
"high": "default"
}
}
}
},
"huggingface": {
"deepseek-ai/DeepSeek-R1": {
"id": "deepseek-ai/DeepSeek-R1",
"name": "DeepSeek R1",
"api": "openai-completions",
"provider": "huggingface",
"baseUrl": "https://router.huggingface.co/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 3,
"output": 7,
"cacheRead": 3,
"cacheWrite": 3
},
"contextWindow": 131072,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek-ai/DeepSeek-R1-0528": {
"id": "deepseek-ai/DeepSeek-R1-0528",
"name": "DeepSeek-R1-0528",
"api": "openai-completions",
"provider": "huggingface",
"baseUrl": "https://router.huggingface.co/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 3,
"output": 5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 163840,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek-ai/DeepSeek-V3.1": {
"id": "deepseek-ai/DeepSeek-V3.1",
"name": "DeepSeek V3.1",
"api": "openai-completions",
"provider": "huggingface",
"baseUrl": "https://router.huggingface.co/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 1.25,
"cacheRead": 0.6,
"cacheWrite": 0.6
},
"contextWindow": 131072,
"maxTokens": 8192
},
"deepseek-ai/DeepSeek-V3.2": {
"id": "deepseek-ai/DeepSeek-V3.2",
"name": "DeepSeek-V3.2",
"api": "openai-completions",
"provider": "huggingface",
"baseUrl": "https://router.huggingface.co/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.28,
"output": 0.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek-ai/DeepSeek-V4-Pro": {
"id": "deepseek-ai/DeepSeek-V4-Pro",
"name": "DeepSeek V4 Pro",
"api": "openai-completions",
"provider": "huggingface",
"baseUrl": "https://router.huggingface.co/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.435,
"output": 0.87,
"cacheRead": 0.003625,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 393216,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"meta-llama/Llama-3.3-70B-Instruct-Turbo": {
"id": "meta-llama/Llama-3.3-70B-Instruct-Turbo",
"name": "Llama 3.3 70B",
"api": "openai-completions",
"provider": "huggingface",
"baseUrl": "https://router.huggingface.co/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.88,
"output": 0.88,
"cacheRead": 0.88,
"cacheWrite": 0.88
},
"contextWindow": 131072,
"maxTokens": 8192
},
"MiniMaxAI/MiniMax-M2.1": {
"id": "MiniMaxAI/MiniMax-M2.1",
"name": "MiniMax-M2.1",
"api": "openai-completions",
"provider": "huggingface",
"baseUrl": "https://router.huggingface.co/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"MiniMaxAI/MiniMax-M2.5": {
"id": "MiniMaxAI/MiniMax-M2.5",
"name": "MiniMax-M2.5",
"api": "openai-completions",
"provider": "huggingface",
"baseUrl": "https://router.huggingface.co/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.03,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"MiniMaxAI/MiniMax-M2.7": {
"id": "MiniMaxAI/MiniMax-M2.7",
"name": "MiniMax-M2.7",
"api": "openai-completions",
"provider": "huggingface",
"baseUrl": "https://router.huggingface.co/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.06,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"moonshotai/Kimi-K2-Instruct": {
"id": "moonshotai/Kimi-K2-Instruct",
"name": "Kimi-K2-Instruct",
"api": "openai-completions",
"provider": "huggingface",
"baseUrl": "https://router.huggingface.co/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384
},
"moonshotai/Kimi-K2-Instruct-0905": {
"id": "moonshotai/Kimi-K2-Instruct-0905",
"name": "Kimi-K2-Instruct-0905",
"api": "openai-completions",
"provider": "huggingface",
"baseUrl": "https://router.huggingface.co/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 16384
},
"moonshotai/Kimi-K2-Thinking": {
"id": "moonshotai/Kimi-K2-Thinking",
"name": "Kimi-K2-Thinking",
"api": "openai-completions",
"provider": "huggingface",
"baseUrl": "https://router.huggingface.co/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.5,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"moonshotai/Kimi-K2.5": {
"id": "moonshotai/Kimi-K2.5",
"name": "Kimi-K2.5",
"api": "openai-completions",
"provider": "huggingface",
"baseUrl": "https://router.huggingface.co/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.6,
"output": 3,
"cacheRead": 0.1,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"moonshotai/Kimi-K2.6": {
"id": "moonshotai/Kimi-K2.6",
"name": "Kimi-K2.6",
"api": "openai-completions",
"provider": "huggingface",
"baseUrl": "https://router.huggingface.co/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.95,
"output": 4,
"cacheRead": 0.16,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-oss-120b": {
"id": "openai/gpt-oss-120b",
"name": "GPT OSS 120B",
"api": "openai-completions",
"provider": "huggingface",
"baseUrl": "https://router.huggingface.co/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
]
}
},
"Qwen/Qwen3-235B-A22B-Thinking-2507": {
"id": "Qwen/Qwen3-235B-A22B-Thinking-2507",
"name": "Qwen3-235B-A22B-Thinking-2507",
"api": "openai-completions",
"provider": "huggingface",
"baseUrl": "https://router.huggingface.co/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"Qwen/Qwen3-Coder-480B-A35B-Instruct": {
"id": "Qwen/Qwen3-Coder-480B-A35B-Instruct",
"name": "Qwen3-Coder-480B-A35B-Instruct",
"api": "openai-completions",
"provider": "huggingface",
"baseUrl": "https://router.huggingface.co/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 2,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 66536
},
"Qwen/Qwen3-Coder-Next": {
"id": "Qwen/Qwen3-Coder-Next",
"name": "Qwen3-Coder-Next",
"api": "openai-completions",
"provider": "huggingface",
"baseUrl": "https://router.huggingface.co/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.2,
"output": 1.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536
},
"Qwen/Qwen3-Next-80B-A3B-Instruct": {
"id": "Qwen/Qwen3-Next-80B-A3B-Instruct",
"name": "Qwen3-Next-80B-A3B-Instruct",
"api": "openai-completions",
"provider": "huggingface",
"baseUrl": "https://router.huggingface.co/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.25,
"output": 1,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 66536
},
"Qwen/Qwen3-Next-80B-A3B-Thinking": {
"id": "Qwen/Qwen3-Next-80B-A3B-Thinking",
"name": "Qwen3-Next-80B-A3B-Thinking",
"api": "openai-completions",
"provider": "huggingface",
"baseUrl": "https://router.huggingface.co/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 131072
},
"Qwen/Qwen3.5-397B-A17B": {
"id": "Qwen/Qwen3.5-397B-A17B",
"name": "Qwen3.5-397B-A17B",
"api": "openai-completions",
"provider": "huggingface",
"baseUrl": "https://router.huggingface.co/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.6,
"output": 3.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"XiaomiMiMo/MiMo-V2-Flash": {
"id": "XiaomiMiMo/MiMo-V2-Flash",
"name": "MiMo-V2-Flash",
"api": "openai-completions",
"provider": "huggingface",
"baseUrl": "https://router.huggingface.co/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.1,
"output": 0.3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 4096,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai-org/GLM-4.7": {
"id": "zai-org/GLM-4.7",
"name": "GLM-4.7",
"api": "openai-completions",
"provider": "huggingface",
"baseUrl": "https://router.huggingface.co/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.2,
"cacheRead": 0.11,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai-org/GLM-4.7-Flash": {
"id": "zai-org/GLM-4.7-Flash",
"name": "GLM-4.7-Flash",
"api": "openai-completions",
"provider": "huggingface",
"baseUrl": "https://router.huggingface.co/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai-org/GLM-5": {
"id": "zai-org/GLM-5",
"name": "GLM-5",
"api": "openai-completions",
"provider": "huggingface",
"baseUrl": "https://router.huggingface.co/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 3.2,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai-org/GLM-5.1": {
"id": "zai-org/GLM-5.1",
"name": "GLM-5.1",
"api": "openai-completions",
"provider": "huggingface",
"baseUrl": "https://router.huggingface.co/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 3.2,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
}
},
"kilo": {
"~anthropic/claude-fable-latest": {
"id": "~anthropic/claude-fable-latest",
"name": "Claude Fable Latest",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"~anthropic/claude-haiku-latest": {
"id": "~anthropic/claude-haiku-latest",
"name": "Claude Haiku Latest",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1,
"output": 5,
"cacheRead": 0.1,
"cacheWrite": 1.25
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"~anthropic/claude-opus-latest": {
"id": "~anthropic/claude-opus-latest",
"name": "Claude Opus Latest",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"~anthropic/claude-sonnet-latest": {
"id": "~anthropic/claude-sonnet-latest",
"name": "Claude Sonnet Latest",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"~google/gemini-flash-latest": {
"id": "~google/gemini-flash-latest",
"name": "Gemini Flash Latest",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.5,
"output": 3,
"cacheRead": 0.05,
"cacheWrite": 0.08333333333333334
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"~google/gemini-pro-latest": {
"id": "~google/gemini-pro-latest",
"name": "Gemini Pro Latest",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 12,
"cacheRead": 0.2,
"cacheWrite": 0.375
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"~moonshotai/kimi-latest": {
"id": "~moonshotai/kimi-latest",
"name": "Kimi Latest",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.74,
"output": 3.49,
"cacheRead": 0.14,
"cacheWrite": 0
},
"contextWindow": 262142,
"maxTokens": 262142,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"~openai/gpt-latest": {
"id": "~openai/gpt-latest",
"name": "GPT Latest",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 30,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"~openai/gpt-mini-latest": {
"id": "~openai/gpt-mini-latest",
"name": "GPT Mini Latest",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.75,
"output": 4.5,
"cacheRead": 0.075,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"ai21/jamba-large-1.7": {
"id": "ai21/jamba-large-1.7",
"name": "Jamba Large 1.7",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 2,
"output": 8,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 4096
},
"aion-labs/aion-1.0": {
"id": "aion-labs/aion-1.0",
"name": "Aion-1.0",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aion-labs/aion-1.0-mini": {
"id": "aion-labs/aion-1.0-mini",
"name": "Aion-1.0-Mini",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aion-labs/aion-2.0": {
"id": "aion-labs/aion-2.0",
"name": "Aion-2.0",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aion-labs/aion-rp-llama-3.1-8b": {
"id": "aion-labs/aion-rp-llama-3.1-8b",
"name": "Aion-RP 1.0 (8B)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"alfredpros/codellama-7b-instruct-solidity": {
"id": "alfredpros/codellama-7b-instruct-solidity",
"name": "CodeLLaMa 7B Instruct Solidity",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"alibaba/tongyi-deepresearch-30b-a3b": {
"id": "alibaba/tongyi-deepresearch-30b-a3b",
"name": "Tongyi DeepResearch 30B A3B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072
},
"allenai/molmo-2-8b": {
"id": "allenai/molmo-2-8b",
"name": "Molmo2 8B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"allenai/olmo-2-0325-32b-instruct": {
"id": "allenai/olmo-2-0325-32b-instruct",
"name": "Olmo 2 32B Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"allenai/olmo-3-32b-think": {
"id": "allenai/olmo-3-32b-think",
"name": "Olmo 3 32B Think",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"allenai/olmo-3-7b-instruct": {
"id": "allenai/olmo-3-7b-instruct",
"name": "Olmo 3 7B Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"allenai/olmo-3-7b-think": {
"id": "allenai/olmo-3-7b-think",
"name": "Olmo 3 7B Think",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"allenai/olmo-3.1-32b-instruct": {
"id": "allenai/olmo-3.1-32b-instruct",
"name": "Olmo 3.1 32B Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"allenai/olmo-3.1-32b-think": {
"id": "allenai/olmo-3.1-32b-think",
"name": "Olmo 3.1 32B Think",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"alpindale/goliath-120b": {
"id": "alpindale/goliath-120b",
"name": "Goliath 120B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"amazon/nova-2-lite-v1": {
"id": "amazon/nova-2-lite-v1",
"name": "Nova 2 Lite",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 2.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65535,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"amazon/nova-lite-v1": {
"id": "amazon/nova-lite-v1",
"name": "Nova Lite 1.0",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.06,
"output": 0.24,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 300000,
"maxTokens": 5120
},
"amazon/nova-micro-v1": {
"id": "amazon/nova-micro-v1",
"name": "Nova Micro 1.0",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.035,
"output": 0.14,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 5120
},
"amazon/nova-premier-v1": {
"id": "amazon/nova-premier-v1",
"name": "Nova Premier 1.0",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 12.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 32000
},
"amazon/nova-pro-v1": {
"id": "amazon/nova-pro-v1",
"name": "Nova Pro 1.0",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.8,
"output": 3.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 300000,
"maxTokens": 5120
},
"anthracite-org/magnum-v4-72b": {
"id": "anthracite-org/magnum-v4-72b",
"name": "Magnum v4 72B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"anthropic/claude-3-haiku": {
"id": "anthropic/claude-3-haiku",
"name": "Claude 3 Haiku",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 1.25,
"cacheRead": 0.03,
"cacheWrite": 0.3
},
"contextWindow": 200000,
"maxTokens": 4096
},
"anthropic/claude-3.5-haiku": {
"id": "anthropic/claude-3.5-haiku",
"name": "Claude 3.5 Haiku",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.8,
"output": 4,
"cacheRead": 0.08,
"cacheWrite": 1
},
"contextWindow": 200000,
"maxTokens": 8192
},
"anthropic/claude-3.5-sonnet": {
"id": "anthropic/claude-3.5-sonnet",
"name": "Claude Sonnet 3.5 v2",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 8192
},
"anthropic/claude-3.7-sonnet": {
"id": "anthropic/claude-3.7-sonnet",
"name": "Claude 3.7 Sonnet",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-3.7-sonnet:thinking": {
"id": "anthropic/claude-3.7-sonnet:thinking",
"name": "Claude 3.7 Sonnet (thinking)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000
},
"anthropic/claude-fable-5": {
"id": "anthropic/claude-fable-5",
"name": "Claude Fable 5",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-haiku-4.5": {
"id": "anthropic/claude-haiku-4.5",
"name": "Claude Haiku 4.5",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1,
"output": 5,
"cacheRead": 0.1,
"cacheWrite": 1.25
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-opus-4": {
"id": "anthropic/claude-opus-4",
"name": "Claude Opus 4",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 75,
"cacheRead": 1.5,
"cacheWrite": 18.75
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-opus-4.1": {
"id": "anthropic/claude-opus-4.1",
"name": "Claude Opus 4.1",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 75,
"cacheRead": 1.5,
"cacheWrite": 18.75
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-opus-4.5": {
"id": "anthropic/claude-opus-4.5",
"name": "Claude Opus 4.5",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-opus-4.6": {
"id": "anthropic/claude-opus-4.6",
"name": "Claude Opus 4.6",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-opus-4.6-fast": {
"id": "anthropic/claude-opus-4.6-fast",
"name": "Claude Opus 4.6 (Fast)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 30,
"output": 150,
"cacheRead": 3,
"cacheWrite": 37.5
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-opus-4.7": {
"id": "anthropic/claude-opus-4.7",
"name": "Claude Opus 4.7",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-opus-4.7-fast": {
"id": "anthropic/claude-opus-4.7-fast",
"name": "Claude Opus 4.7 (Fast)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 30,
"output": 150,
"cacheRead": 3,
"cacheWrite": 37.5
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-opus-4.8": {
"id": "anthropic/claude-opus-4.8",
"name": "Claude Opus 4.8",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-opus-4.8-fast": {
"id": "anthropic/claude-opus-4.8-fast",
"name": "Claude Opus 4.8 (Fast)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000
},
"anthropic/claude-sonnet-4": {
"id": "anthropic/claude-sonnet-4",
"name": "Claude Sonnet 4",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-sonnet-4.5": {
"id": "anthropic/claude-sonnet-4.5",
"name": "Claude Sonnet 4.5",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-sonnet-4.6": {
"id": "anthropic/claude-sonnet-4.6",
"name": "Claude Sonnet 4.6",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"arcee-ai/coder-large": {
"id": "arcee-ai/coder-large",
"name": "Coder Large",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"arcee-ai/maestro-reasoning": {
"id": "arcee-ai/maestro-reasoning",
"name": "Maestro Reasoning",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"arcee-ai/spotlight": {
"id": "arcee-ai/spotlight",
"name": "Spotlight",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"arcee-ai/trinity-large-preview": {
"id": "arcee-ai/trinity-large-preview",
"name": "Trinity Large Preview",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131000,
"maxTokens": 131000
},
"arcee-ai/trinity-large-preview:free": {
"id": "arcee-ai/trinity-large-preview:free",
"name": "Trinity Large Preview (free)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131000,
"maxTokens": 131000
},
"arcee-ai/trinity-large-thinking": {
"id": "arcee-ai/trinity-large-thinking",
"name": "Trinity Large Thinking",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.22,
"output": 0.85,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"arcee-ai/trinity-large-thinking:free": {
"id": "arcee-ai/trinity-large-thinking:free",
"name": "Trinity Large Thinking (free)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 80000
},
"arcee-ai/trinity-mini": {
"id": "arcee-ai/trinity-mini",
"name": "Trinity Mini",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.045,
"output": 0.15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"arcee-ai/virtuoso-large": {
"id": "arcee-ai/virtuoso-large",
"name": "Virtuoso Large",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.75,
"output": 1.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 64000
},
"baidu/cobuddy:free": {
"id": "baidu/cobuddy:free",
"name": "CoBuddy (free)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"baidu/ernie-4.5-21b-a3b": {
"id": "baidu/ernie-4.5-21b-a3b",
"name": "ERNIE 4.5 21B A3B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.07,
"output": 0.28,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 120000,
"maxTokens": 8000
},
"baidu/ernie-4.5-300b-a47b": {
"id": "baidu/ernie-4.5-300b-a47b",
"name": "ERNIE 4.5 300B A47B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"baidu/ernie-4.5-vl-28b-a3b": {
"id": "baidu/ernie-4.5-vl-28b-a3b",
"name": "ERNIE 4.5 VL 28B A3B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.14,
"output": 0.56,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 30000,
"maxTokens": 8000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"baidu/ernie-4.5-vl-424b-a47b": {
"id": "baidu/ernie-4.5-vl-424b-a47b",
"name": "ERNIE 4.5 VL 424B A47B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"baidu/qianfan-ocr-fast": {
"id": "baidu/qianfan-ocr-fast",
"name": "Qianfan-OCR-Fast",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"baidu/qianfan-ocr-fast:free": {
"id": "baidu/qianfan-ocr-fast:free",
"name": "Qianfan-OCR-Fast (free)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"bytedance-seed/dola-seed-2.0-pro:free": {
"id": "bytedance-seed/dola-seed-2.0-pro:free",
"name": "Dola Seed 2.0 Pro (free)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"bytedance-seed/seed-1.6": {
"id": "bytedance-seed/seed-1.6",
"name": "Seed 1.6",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"bytedance-seed/seed-1.6-flash": {
"id": "bytedance-seed/seed-1.6-flash",
"name": "Seed 1.6 Flash",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.075,
"output": 0.3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"bytedance-seed/seed-2.0-lite": {
"id": "bytedance-seed/seed-2.0-lite",
"name": "Seed-2.0-Lite",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"bytedance-seed/seed-2.0-mini": {
"id": "bytedance-seed/seed-2.0-mini",
"name": "Seed-2.0-Mini",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1,
"output": 0.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"bytedance/ui-tars-1.5-7b": {
"id": "bytedance/ui-tars-1.5-7b",
"name": "UI-TARS 7B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"cohere/command-a": {
"id": "cohere/command-a",
"name": "Command A",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"cohere/command-r-08-2024": {
"id": "cohere/command-r-08-2024",
"name": "Command R (08-2024)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4000
},
"cohere/command-r-plus-08-2024": {
"id": "cohere/command-r-plus-08-2024",
"name": "Command R+ (08-2024)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 2.5,
"output": 10,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4000
},
"cohere/command-r7b-12-2024": {
"id": "cohere/command-r7b-12-2024",
"name": "Command R7B (12-2024)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.0375,
"output": 0.15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4000
},
"corethink:free": {
"id": "corethink:free",
"name": "CoreThink (free)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"deepcogito/cogito-v2.1-671b": {
"id": "deepcogito/cogito-v2.1-671b",
"name": "Cogito v2.1 671B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"deepseek/deepseek-chat": {
"id": "deepseek/deepseek-chat",
"name": "DeepSeek V3",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.32,
"output": 0.89,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 163840
},
"deepseek/deepseek-chat-v3-0324": {
"id": "deepseek/deepseek-chat-v3-0324",
"name": "DeepSeek V3 0324",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.2,
"output": 0.77,
"cacheRead": 0.095,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek/deepseek-chat-v3.1": {
"id": "deepseek/deepseek-chat-v3.1",
"name": "DeepSeek V3.1",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.75,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32768,
"maxTokens": 7168,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek/deepseek-r1": {
"id": "deepseek/deepseek-r1",
"name": "R1",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.7,
"output": 2.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 64000,
"maxTokens": 16000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek/deepseek-r1-0528": {
"id": "deepseek/deepseek-r1-0528",
"name": "R1 0528",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.45,
"output": 2.15,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek/deepseek-r1-distill-llama-70b": {
"id": "deepseek/deepseek-r1-distill-llama-70b",
"name": "R1 Distill Llama 70B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192
},
"deepseek/deepseek-r1-distill-qwen-32b": {
"id": "deepseek/deepseek-r1-distill-qwen-32b",
"name": "R1 Distill Qwen 32B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"deepseek/deepseek-v3.1-terminus": {
"id": "deepseek/deepseek-v3.1-terminus",
"name": "DeepSeek V3.1 Terminus",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.21,
"output": 0.79,
"cacheRead": 0.13,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek/deepseek-v3.1-terminus:exacto": {
"id": "deepseek/deepseek-v3.1-terminus:exacto",
"name": "DeepSeek V3.1 Terminus (exacto)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 32768
},
"deepseek/deepseek-v3.2": {
"id": "deepseek/deepseek-v3.2",
"name": "DeepSeek V3.2",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.26,
"output": 0.38,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek/deepseek-v3.2-exp": {
"id": "deepseek/deepseek-v3.2-exp",
"name": "DeepSeek V3.2 Exp",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.27,
"output": 0.41,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek/deepseek-v3.2-speciale": {
"id": "deepseek/deepseek-v3.2-speciale",
"name": "DeepSeek V3.2 Speciale",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"deepseek/deepseek-v4-flash": {
"id": "deepseek/deepseek-v4-flash",
"name": "DeepSeek V4 Flash",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.14,
"output": 0.28,
"cacheRead": 0.0028,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 384000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek/deepseek-v4-flash:discounted": {
"id": "deepseek/deepseek-v4-flash:discounted",
"name": "DeepSeek V4 Flash",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 384000
},
"deepseek/deepseek-v4-flash:free": {
"id": "deepseek/deepseek-v4-flash:free",
"name": "DeepSeek V4 Flash (free)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 384000
},
"deepseek/deepseek-v4-pro": {
"id": "deepseek/deepseek-v4-pro",
"name": "DeepSeek V4 Pro",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.435,
"output": 0.87,
"cacheRead": 0.003625,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 384000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek/deepseek-v4-pro:discounted": {
"id": "deepseek/deepseek-v4-pro:discounted",
"name": "DeepSeek V4 Pro",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 384000
},
"eleutherai/llemma_7b": {
"id": "eleutherai/llemma_7b",
"name": "Llemma 7b",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"essentialai/rnj-1-instruct": {
"id": "essentialai/rnj-1-instruct",
"name": "Rnj 1 Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32768,
"maxTokens": 6554
},
"giga-potato": {
"id": "giga-potato",
"name": "Giga Potato (free)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortRouting": {
"off": "giga-potato",
"minimal": "giga-potato-thinking",
"low": "giga-potato-thinking",
"medium": "giga-potato-thinking",
"high": "giga-potato-thinking",
"xhigh": "giga-potato-thinking"
}
},
"compat": {
"supportsStore": false,
"supportsDeveloperRole": false,
"supportsMultipleSystemMessages": false,
"supportsReasoningEffort": true,
"supportsReasoningParams": true,
"reasoningEffortMap": {},
"supportsUsageInStreaming": true,
"alwaysSendMaxTokens": false,
"disableReasoningOnForcedToolChoice": false,
"disableReasoningOnToolChoice": false,
"supportsToolChoice": true,
"maxTokensField": "max_completion_tokens",
"requiresToolResultName": false,
"requiresAssistantAfterToolResult": false,
"requiresThinkingAsText": false,
"requiresMistralToolIds": false,
"thinkingFormat": "openai",
"reasoningContentField": "reasoning_content",
"requiresReasoningContentForToolCalls": false,
"allowsSyntheticReasoningContentForToolCalls": true,
"requiresAssistantContentForToolCalls": false,
"isOpenRouterHost": false,
"isVercelGatewayHost": false,
"supportsStrictMode": false,
"toolStrictMode": "mixed"
}
},
"google/gemini-2.0-flash-001": {
"id": "google/gemini-2.0-flash-001",
"name": "Gemini 2.0 Flash",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1,
"output": 0.4,
"cacheRead": 0.025,
"cacheWrite": 0.083333
},
"contextWindow": 1048576,
"maxTokens": 8192
},
"google/gemini-2.0-flash-lite-001": {
"id": "google/gemini-2.0-flash-lite-001",
"name": "Gemini 2.0 Flash Lite",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.075,
"output": 0.3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 8192
},
"google/gemini-2.5-flash": {
"id": "google/gemini-2.5-flash",
"name": "Gemini 2.5 Flash",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 2.5,
"cacheRead": 0.03,
"cacheWrite": 0.083333
},
"contextWindow": 1048576,
"maxTokens": 65535,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"google/gemini-2.5-flash-image": {
"id": "google/gemini-2.5-flash-image",
"name": "Nano Banana (Gemini 2.5 Flash Image)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"google/gemini-2.5-flash-lite": {
"id": "google/gemini-2.5-flash-lite",
"name": "Gemini 2.5 Flash Lite",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1,
"output": 0.4,
"cacheRead": 0.01,
"cacheWrite": 0.083333
},
"contextWindow": 1048576,
"maxTokens": 65535,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"google/gemini-2.5-flash-lite-preview-09-2025": {
"id": "google/gemini-2.5-flash-lite-preview-09-2025",
"name": "Gemini 2.5 Flash Lite Preview 09-2025",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1,
"output": 0.4,
"cacheRead": 0.01,
"cacheWrite": 0.083333
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"google/gemini-2.5-pro": {
"id": "google/gemini-2.5-pro",
"name": "Gemini 2.5 Pro",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0.375
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"google/gemini-2.5-pro-preview": {
"id": "google/gemini-2.5-pro-preview",
"name": "Gemini 2.5 Pro Preview 06-05",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0.375
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"google/gemini-2.5-pro-preview-05-06": {
"id": "google/gemini-2.5-pro-preview-05-06",
"name": "Gemini 2.5 Pro Preview 05-06",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0.375
},
"contextWindow": 1048576,
"maxTokens": 65535,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3-flash-preview": {
"id": "google/gemini-3-flash-preview",
"name": "Gemini 3 Flash Preview",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.5,
"output": 3,
"cacheRead": 0.05,
"cacheWrite": 0.083333
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3-pro-image-preview": {
"id": "google/gemini-3-pro-image-preview",
"name": "Nano Banana Pro (Gemini 3 Pro Image Preview)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3-pro-preview": {
"id": "google/gemini-3-pro-preview",
"name": "Gemini 3 Pro Preview",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3.1-flash-image-preview": {
"id": "google/gemini-3.1-flash-image-preview",
"name": "Nano Banana 2 (Gemini 3.1 Flash Image Preview)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"google/gemini-3.1-flash-lite": {
"id": "google/gemini-3.1-flash-lite",
"name": "Gemini 3.1 Flash Lite",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 1.5,
"cacheRead": 0.025,
"cacheWrite": 0.08333
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3.1-flash-lite-preview": {
"id": "google/gemini-3.1-flash-lite-preview",
"name": "Gemini 3.1 Flash Lite Preview",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 1.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3.1-pro-preview": {
"id": "google/gemini-3.1-pro-preview",
"name": "Gemini 3.1 Pro Preview",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 12,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3.1-pro-preview-customtools": {
"id": "google/gemini-3.1-pro-preview-customtools",
"name": "Gemini 3.1 Pro Preview Custom Tools",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 12,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3.5-flash": {
"id": "google/gemini-3.5-flash",
"name": "Gemini 3.5 Flash",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.5,
"output": 9,
"cacheRead": 0.15,
"cacheWrite": 0.08333
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"google/gemma-2-27b-it": {
"id": "google/gemma-2-27b-it",
"name": "Gemma 2 27B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"google/gemma-2-9b-it": {
"id": "google/gemma-2-9b-it",
"name": "Gemma 2 9B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"google/gemma-3-12b-it": {
"id": "google/gemma-3-12b-it",
"name": "Gemma 3 12B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384
},
"google/gemma-3-27b-it": {
"id": "google/gemma-3-27b-it",
"name": "Gemma 3 27B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.03,
"output": 0.11,
"cacheRead": 0.02,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 65536
},
"google/gemma-3-4b-it": {
"id": "google/gemma-3-4b-it",
"name": "Gemma 3 4B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"google/gemma-3n-e4b-it": {
"id": "google/gemma-3n-e4b-it",
"name": "Gemma 3n E4b It",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"google/gemma-4-26b-a4b-it": {
"id": "google/gemma-4-26b-a4b-it",
"name": "Gemma 4 26B A4B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.12,
"output": 0.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"google/gemma-4-31b-it": {
"id": "google/gemma-4-31b-it",
"name": "Gemma 4 31B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.14,
"output": 0.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"google/lyria-3-clip-preview": {
"id": "google/lyria-3-clip-preview",
"name": "Lyria 3 Clip Preview",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"google/lyria-3-pro-preview": {
"id": "google/lyria-3-pro-preview",
"name": "Lyria 3 Pro Preview",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gryphe/mythomax-l2-13b": {
"id": "gryphe/mythomax-l2-13b",
"name": "MythoMax 13B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"ibm-granite/granite-4.0-h-micro": {
"id": "ibm-granite/granite-4.0-h-micro",
"name": "Granite 4.0 Micro",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"ibm-granite/granite-4.1-8b": {
"id": "ibm-granite/granite-4.1-8b",
"name": "Granite 4.1 8B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.05,
"output": 0.1,
"cacheRead": 0.05,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072
},
"inception/mercury": {
"id": "inception/mercury",
"name": "Mercury",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 32000
},
"inception/mercury-2": {
"id": "inception/mercury-2",
"name": "Mercury 2",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.25,
"output": 0.75,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 50000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"inception/mercury-coder": {
"id": "inception/mercury-coder",
"name": "Mercury Coder",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 32000
},
"inclusionai/ling-2.6-1t": {
"id": "inclusionai/ling-2.6-1t",
"name": "Ling-2.6-1T",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 2.5,
"cacheRead": 0.06,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768
},
"inclusionai/ling-2.6-1t:free": {
"id": "inclusionai/ling-2.6-1t:free",
"name": "Ling-2.6-1T (free)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768
},
"inclusionai/ling-2.6-flash": {
"id": "inclusionai/ling-2.6-flash",
"name": "Ling-2.6 Flash",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.08,
"output": 0.24,
"cacheRead": 0.016,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768
},
"inclusionai/ling-2.6-flash:free": {
"id": "inclusionai/ling-2.6-flash:free",
"name": "Ling-2.6-flash (free)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768
},
"inclusionai/ring-2.6-1t": {
"id": "inclusionai/ring-2.6-1t",
"name": "Ring-2.6-1T",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.075,
"output": 0.625,
"cacheRead": 0.015,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"inclusionai/ring-2.6-1t:free": {
"id": "inclusionai/ring-2.6-1t:free",
"name": "Ring-2.6-1T (free)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536
},
"inflection/inflection-3-pi": {
"id": "inflection/inflection-3-pi",
"name": "Inflection 3 Pi",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"inflection/inflection-3-productivity": {
"id": "inflection/inflection-3-productivity",
"name": "Inflection 3 Productivity",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"kilo-auto/balanced": {
"id": "kilo-auto/balanced",
"name": "Kilo Auto Balanced",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"kilo-auto/free": {
"id": "kilo-auto/free",
"name": "Kilo Auto Free",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"kilo-auto/frontier": {
"id": "kilo-auto/frontier",
"name": "Kilo Auto Frontier",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"kilo-auto/small": {
"id": "kilo-auto/small",
"name": "Kilo Auto Small",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.05,
"output": 0.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"kilo/auto": {
"id": "kilo/auto",
"name": "Deprecated Kilo Auto Frontier",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 30000
},
"kilo/auto-free": {
"id": "kilo/auto-free",
"name": "Deprecated Kilo Auto Free",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 30000
},
"kilo/auto-small": {
"id": "kilo/auto-small",
"name": "Deprecated Kilo Auto Small",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"kwaipilot/kat-coder-pro": {
"id": "kwaipilot/kat-coder-pro",
"name": "KAT-Coder-Pro V1",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"kwaipilot/kat-coder-pro-v2": {
"id": "kwaipilot/kat-coder-pro-v2",
"name": "KAT-Coder-Pro V2",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.06,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 80000
},
"liquid/lfm-2-24b-a2b": {
"id": "liquid/lfm-2-24b-a2b",
"name": "LFM2-24B-A2B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"liquid/lfm-2.2-6b": {
"id": "liquid/lfm-2.2-6b",
"name": "LFM2-2.6B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"liquid/lfm2-8b-a1b": {
"id": "liquid/lfm2-8b-a1b",
"name": "LFM2-8B-A1B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"mancer/weaver": {
"id": "mancer/weaver",
"name": "Weaver (alpha)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"meituan/longcat-flash-chat": {
"id": "meituan/longcat-flash-chat",
"name": "LongCat Flash Chat",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072
},
"meta-llama/llama-3-70b-instruct": {
"id": "meta-llama/llama-3-70b-instruct",
"name": "Llama 3 70B Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"meta-llama/llama-3-8b-instruct": {
"id": "meta-llama/llama-3-8b-instruct",
"name": "Llama 3 8B Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.03,
"output": 0.04,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 8192,
"maxTokens": 16384
},
"meta-llama/llama-3.1-405b": {
"id": "meta-llama/llama-3.1-405b",
"name": "Llama 3.1 405B (base)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"meta-llama/llama-3.1-405b-instruct": {
"id": "meta-llama/llama-3.1-405b-instruct",
"name": "Llama 3.1 405B Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131000,
"maxTokens": null
},
"meta-llama/llama-3.1-70b-instruct": {
"id": "meta-llama/llama-3.1-70b-instruct",
"name": "Llama 3.1 70B Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.4,
"output": 0.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 26215
},
"meta-llama/llama-3.1-8b-instruct": {
"id": "meta-llama/llama-3.1-8b-instruct",
"name": "Llama 3.1 8B Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.02,
"output": 0.05,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 16384,
"maxTokens": 16384
},
"meta-llama/llama-3.2-11b-vision-instruct": {
"id": "meta-llama/llama-3.2-11b-vision-instruct",
"name": "Llama 3.2 11B Vision Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"meta-llama/llama-3.2-1b-instruct": {
"id": "meta-llama/llama-3.2-1b-instruct",
"name": "Llama 3.2 1B Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"meta-llama/llama-3.2-3b-instruct": {
"id": "meta-llama/llama-3.2-3b-instruct",
"name": "Llama 3.2 3B Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"meta-llama/llama-3.3-70b-instruct": {
"id": "meta-llama/llama-3.3-70b-instruct",
"name": "Llama 3.3 70B Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.1,
"output": 0.32,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384
},
"meta-llama/llama-4-maverick": {
"id": "meta-llama/llama-4-maverick",
"name": "Llama 4 Maverick",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 16384
},
"meta-llama/llama-4-scout": {
"id": "meta-llama/llama-4-scout",
"name": "Llama 4 Scout",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.08,
"output": 0.3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 327680,
"maxTokens": 16384
},
"meta-llama/llama-guard-2-8b": {
"id": "meta-llama/llama-guard-2-8b",
"name": "LlamaGuard 2 8B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"meta-llama/llama-guard-3-8b": {
"id": "meta-llama/llama-guard-3-8b",
"name": "Llama Guard 3 8B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"meta-llama/llama-guard-4-12b": {
"id": "meta-llama/llama-guard-4-12b",
"name": "Llama Guard 4 12B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"meta-llama/llama-guard-4-12b:free": {
"id": "meta-llama/llama-guard-4-12b:free",
"name": "Llama Guard 4 12B (free)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"microsoft/phi-4": {
"id": "microsoft/phi-4",
"name": "Phi 4",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"microsoft/phi-4-mini-instruct": {
"id": "microsoft/phi-4-mini-instruct",
"name": "Phi-4-Mini",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192
},
"microsoft/wizardlm-2-8x22b": {
"id": "microsoft/wizardlm-2-8x22b",
"name": "WizardLM-2 8x22B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"minimax/minimax-01": {
"id": "minimax/minimax-01",
"name": "MiniMax-01",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"minimax/minimax-m1": {
"id": "minimax/minimax-m1",
"name": "MiniMax M1",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.4,
"output": 2.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 40000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"minimax/minimax-m2": {
"id": "minimax/minimax-m2",
"name": "MiniMax M2",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.255,
"output": 1,
"cacheRead": 0.03,
"cacheWrite": 0
},
"contextWindow": 196608,
"maxTokens": 196608,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax/minimax-m2-her": {
"id": "minimax/minimax-m2-her",
"name": "MiniMax M2-her",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 64000,
"maxTokens": null
},
"minimax/minimax-m2.1": {
"id": "minimax/minimax-m2.1",
"name": "MiniMax M2.1",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.27,
"output": 0.95,
"cacheRead": 0.03,
"cacheWrite": 0
},
"contextWindow": 196608,
"maxTokens": 39322,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax/minimax-m2.5": {
"id": "minimax/minimax-m2.5",
"name": "MiniMax M2.5",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.25,
"output": 1.2,
"cacheRead": 0.029,
"cacheWrite": 0
},
"contextWindow": 196608,
"maxTokens": 196608,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax/minimax-m2.5:free": {
"id": "minimax/minimax-m2.5:free",
"name": "MiniMax M2.5 (free)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072
},
"minimax/minimax-m2.7": {
"id": "minimax/minimax-m2.7",
"name": "MiniMax M2.7",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.06,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax/minimax-m3": {
"id": "minimax/minimax-m3",
"name": "MiniMax-M3",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 512000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"minimax/minimax-m3:discounted": {
"id": "minimax/minimax-m3:discounted",
"name": "MiniMax M3 (50% off through 2026-06-07)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 512000,
"maxTokens": 131072
},
"mistralai/codestral-2508": {
"id": "mistralai/codestral-2508",
"name": "Codestral 2508",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 0.9,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 51200
},
"mistralai/devstral-2512": {
"id": "mistralai/devstral-2512",
"name": "Devstral 2 2512",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.4,
"output": 2,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536
},
"mistralai/devstral-medium": {
"id": "mistralai/devstral-medium",
"name": "Devstral Medium",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.4,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 26215
},
"mistralai/devstral-small": {
"id": "mistralai/devstral-small",
"name": "Devstral Small 1.1",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.1,
"output": 0.3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 26215
},
"mistralai/ministral-14b-2512": {
"id": "mistralai/ministral-14b-2512",
"name": "Ministral 3 14B 2512",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.2,
"output": 0.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 52429
},
"mistralai/ministral-3b-2512": {
"id": "mistralai/ministral-3b-2512",
"name": "Ministral 3 3B 2512",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1,
"output": 0.1,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768
},
"mistralai/ministral-8b-2512": {
"id": "mistralai/ministral-8b-2512",
"name": "Ministral 3 8B 2512",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 0.15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768
},
"mistralai/mistral-7b-instruct": {
"id": "mistralai/mistral-7b-instruct",
"name": "Mistral 7B Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"mistralai/mistral-7b-instruct-v0.1": {
"id": "mistralai/mistral-7b-instruct-v0.1",
"name": "Mistral 7B Instruct v0.1",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"mistralai/mistral-7b-instruct-v0.3": {
"id": "mistralai/mistral-7b-instruct-v0.3",
"name": "Mistral 7B Instruct v0.3",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"mistralai/mistral-large": {
"id": "mistralai/mistral-large",
"name": "Mistral Large",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 2,
"output": 6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 25600
},
"mistralai/mistral-large-2407": {
"id": "mistralai/mistral-large-2407",
"name": "Mistral Large 2407",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 2,
"output": 6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768
},
"mistralai/mistral-large-2411": {
"id": "mistralai/mistral-large-2411",
"name": "Mistral Large 2411",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 2,
"output": 6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 26215
},
"mistralai/mistral-large-2512": {
"id": "mistralai/mistral-large-2512",
"name": "Mistral Large 3 2512",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.5,
"output": 1.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 52429
},
"mistralai/mistral-medium-3": {
"id": "mistralai/mistral-medium-3",
"name": "Mistral Medium 3",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.4,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 26215
},
"mistralai/mistral-medium-3-5": {
"id": "mistralai/mistral-medium-3-5",
"name": "Mistral Medium 3.5",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.5,
"output": 7.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"mistralai/mistral-medium-3.1": {
"id": "mistralai/mistral-medium-3.1",
"name": "Mistral Medium 3.1",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.4,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 26215
},
"mistralai/mistral-nemo": {
"id": "mistralai/mistral-nemo",
"name": "Mistral Nemo",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.02,
"output": 0.04,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384
},
"mistralai/mistral-saba": {
"id": "mistralai/mistral-saba",
"name": "Saba",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.2,
"output": 0.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32768,
"maxTokens": 32768
},
"mistralai/mistral-small-24b-instruct-2501": {
"id": "mistralai/mistral-small-24b-instruct-2501",
"name": "Mistral Small 3",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.05,
"output": 0.08,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32768,
"maxTokens": 16384
},
"mistralai/mistral-small-2603": {
"id": "mistralai/mistral-small-2603",
"name": "Mistral Small 4",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0.015,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"mistralai/mistral-small-3.1-24b-instruct": {
"id": "mistralai/mistral-small-3.1-24b-instruct",
"name": "Mistral Small 3.1 24B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"mistralai/mistral-small-3.2-24b-instruct": {
"id": "mistralai/mistral-small-3.2-24b-instruct",
"name": "Mistral Small 3.2 24B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.06,
"output": 0.18,
"cacheRead": 0.03,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072
},
"mistralai/mistral-small-creative": {
"id": "mistralai/mistral-small-creative",
"name": "Mistral Small Creative",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"mistralai/mixtral-8x22b-instruct": {
"id": "mistralai/mixtral-8x22b-instruct",
"name": "Mixtral 8x22B Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 2,
"output": 6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 65536,
"maxTokens": 13108
},
"mistralai/mixtral-8x7b-instruct": {
"id": "mistralai/mixtral-8x7b-instruct",
"name": "Mixtral 8x7B Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32768,
"maxTokens": 16384
},
"mistralai/pixtral-large-2411": {
"id": "mistralai/pixtral-large-2411",
"name": "Pixtral Large 2411",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768
},
"mistralai/voxtral-small-24b-2507": {
"id": "mistralai/voxtral-small-24b-2507",
"name": "Voxtral Small 24B 2507",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.1,
"output": 0.3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32000,
"maxTokens": 6400
},
"moonshotai/kimi-k2": {
"id": "moonshotai/kimi-k2",
"name": "Kimi K2 0711",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.55,
"output": 2.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131000,
"maxTokens": 26215
},
"moonshotai/kimi-k2-0905": {
"id": "moonshotai/kimi-k2-0905",
"name": "Kimi K2 0905",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.4,
"output": 2,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 26215
},
"moonshotai/kimi-k2-0905:exacto": {
"id": "moonshotai/kimi-k2-0905:exacto",
"name": "Kimi K2 0905 (exacto)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"moonshotai/kimi-k2-thinking": {
"id": "moonshotai/kimi-k2-thinking",
"name": "Kimi K2 Thinking",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.47,
"output": 2,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 65535,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"moonshotai/kimi-k2.5": {
"id": "moonshotai/kimi-k2.5",
"name": "Kimi K2.5",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.45,
"output": 2.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65535,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"moonshotai/kimi-k2.5:free": {
"id": "moonshotai/kimi-k2.5:free",
"name": "Kimi K2.5 (free)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536
},
"moonshotai/kimi-k2.6": {
"id": "moonshotai/kimi-k2.6",
"name": "Kimi K2.6",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.75,
"output": 3.5,
"cacheRead": 0.375,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65535,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"moonshotai/kimi-k2.6:free": {
"id": "moonshotai/kimi-k2.6:free",
"name": "Kimi K2.6 (free)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536
},
"moonshotai/kimi-k2.7-code": {
"id": "moonshotai/kimi-k2.7-code",
"name": "Kimi K2.7 Code",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"morph-warp-grep-v2": {
"id": "morph-warp-grep-v2",
"name": "WarpGrep V2",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"morph/morph-v3-fast": {
"id": "morph/morph-v3-fast",
"name": "Morph V3 Fast",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"morph/morph-v3-large": {
"id": "morph/morph-v3-large",
"name": "Morph V3 Large",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"neversleep/llama-3.1-lumimaid-8b": {
"id": "neversleep/llama-3.1-lumimaid-8b",
"name": "Lumimaid v0.2 8B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"neversleep/noromaid-20b": {
"id": "neversleep/noromaid-20b",
"name": "Noromaid 20B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nex-agi/deepseek-v3.1-nex-n1": {
"id": "nex-agi/deepseek-v3.1-nex-n1",
"name": "DeepSeek V3.1 Nex N1",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.27,
"output": 1,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 163840
},
"nex-agi/nex-n2-pro:free": {
"id": "nex-agi/nex-n2-pro:free",
"name": "Nex-N2-Pro (free)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nousresearch/hermes-2-pro-llama-3-8b": {
"id": "nousresearch/hermes-2-pro-llama-3-8b",
"name": "Hermes 2 Pro - Llama-3 8B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nousresearch/hermes-3-llama-3.1-405b": {
"id": "nousresearch/hermes-3-llama-3.1-405b",
"name": "Hermes 3 405B Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"nousresearch/hermes-3-llama-3.1-70b": {
"id": "nousresearch/hermes-3-llama-3.1-70b",
"name": "Hermes 3 70B Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"nousresearch/hermes-4-405b": {
"id": "nousresearch/hermes-4-405b",
"name": "Hermes 4 405B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nousresearch/hermes-4-70b": {
"id": "nousresearch/hermes-4-70b",
"name": "Hermes 4 70B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072
},
"nvidia/llama-3.1-nemotron-70b-instruct": {
"id": "nvidia/llama-3.1-nemotron-70b-instruct",
"name": "Llama 3.1 Nemotron 70b Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"nvidia/llama-3.1-nemotron-ultra-253b-v1": {
"id": "nvidia/llama-3.1-nemotron-ultra-253b-v1",
"name": "Llama-3.1-Nemotron-Ultra-253B-v1",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nvidia/llama-3.3-nemotron-super-49b-v1.5": {
"id": "nvidia/llama-3.3-nemotron-super-49b-v1.5",
"name": "Llama 3.3 Nemotron Super 49B V1.5",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.1,
"output": 0.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 26215,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nvidia/nemotron-3-nano-30b-a3b": {
"id": "nvidia/nemotron-3-nano-30b-a3b",
"name": "Nemotron 3 Nano 30B A3B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.05,
"output": 0.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 52429,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": {
"id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
"name": "Nemotron 3 Nano Omni (free)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"nvidia/nemotron-3-super-120b-a12b": {
"id": "nvidia/nemotron-3-super-120b-a12b",
"name": "Nemotron 3 Super",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.1,
"output": 0.5,
"cacheRead": 0.1,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nvidia/nemotron-3-super-120b-a12b:free": {
"id": "nvidia/nemotron-3-super-120b-a12b:free",
"name": "Nemotron 3 Super (free)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nvidia/nemotron-3-ultra-550b-a55b": {
"id": "nvidia/nemotron-3-ultra-550b-a55b",
"name": "Nemotron 3 Ultra 550B A55B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nvidia/nemotron-3-ultra-550b-a55b:free": {
"id": "nvidia/nemotron-3-ultra-550b-a55b:free",
"name": "Nemotron 3 Ultra (free)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/nemotron-3.5-content-safety:free": {
"id": "nvidia/nemotron-3.5-content-safety:free",
"name": "Nemotron 3.5 Content Safety (free)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/nemotron-nano-12b-v2-vl": {
"id": "nvidia/nemotron-nano-12b-v2-vl",
"name": "Nemotron Nano 12B 2 VL",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/nemotron-nano-9b-v2": {
"id": "nvidia/nemotron-nano-9b-v2",
"name": "Nemotron Nano 9B V2",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.04,
"output": 0.16,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 26215,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-3.5-turbo": {
"id": "openai/gpt-3.5-turbo",
"name": "GPT-3.5 Turbo",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.5,
"output": 1.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 16385,
"maxTokens": 4096
},
"openai/gpt-3.5-turbo-0613": {
"id": "openai/gpt-3.5-turbo-0613",
"name": "GPT-3.5 Turbo (older v0613)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 4095,
"maxTokens": 4096
},
"openai/gpt-3.5-turbo-16k": {
"id": "openai/gpt-3.5-turbo-16k",
"name": "GPT-3.5 Turbo 16k",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 3,
"output": 4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 16385,
"maxTokens": 4096
},
"openai/gpt-3.5-turbo-instruct": {
"id": "openai/gpt-3.5-turbo-instruct",
"name": "GPT-3.5 Turbo Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"openai/gpt-4": {
"id": "openai/gpt-4",
"name": "GPT-4",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 30,
"output": 60,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 8191,
"maxTokens": 4096
},
"openai/gpt-4-0314": {
"id": "openai/gpt-4-0314",
"name": "GPT-4 (older v0314)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 30,
"output": 60,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 8191,
"maxTokens": 4096
},
"openai/gpt-4-1106-preview": {
"id": "openai/gpt-4-1106-preview",
"name": "GPT-4 Turbo (older v1106)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 10,
"output": 30,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"openai/gpt-4-turbo": {
"id": "openai/gpt-4-turbo",
"name": "GPT-4 Turbo",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 10,
"output": 30,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"openai/gpt-4-turbo-preview": {
"id": "openai/gpt-4-turbo-preview",
"name": "GPT-4 Turbo Preview",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 10,
"output": 30,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"openai/gpt-4.1": {
"id": "openai/gpt-4.1",
"name": "GPT-4.1",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 8,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 1047576,
"maxTokens": 32768
},
"openai/gpt-4.1-mini": {
"id": "openai/gpt-4.1-mini",
"name": "GPT-4.1 Mini",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.4,
"output": 1.6,
"cacheRead": 0.1,
"cacheWrite": 0
},
"contextWindow": 1047576,
"maxTokens": 32768
},
"openai/gpt-4.1-nano": {
"id": "openai/gpt-4.1-nano",
"name": "GPT-4.1 Nano",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1,
"output": 0.4,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 1047576,
"maxTokens": 32768
},
"openai/gpt-4o": {
"id": "openai/gpt-4o",
"name": "GPT-4o",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 10,
"cacheRead": 1.25,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-4o-2024-05-13": {
"id": "openai/gpt-4o-2024-05-13",
"name": "GPT-4o (2024-05-13)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"openai/gpt-4o-2024-08-06": {
"id": "openai/gpt-4o-2024-08-06",
"name": "GPT-4o (2024-08-06)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 10,
"cacheRead": 1.25,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-4o-2024-11-20": {
"id": "openai/gpt-4o-2024-11-20",
"name": "GPT-4o (2024-11-20)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 10,
"cacheRead": 1.25,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-4o-audio-preview": {
"id": "openai/gpt-4o-audio-preview",
"name": "GPT-4o Audio",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 2.5,
"output": 10,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-4o-mini": {
"id": "openai/gpt-4o-mini",
"name": "GPT-4o-mini",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0.075,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-4o-mini-2024-07-18": {
"id": "openai/gpt-4o-mini-2024-07-18",
"name": "GPT-4o-mini (2024-07-18)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-4o-mini-search-preview": {
"id": "openai/gpt-4o-mini-search-preview",
"name": "GPT-4o-mini Search Preview",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"openai/gpt-4o-search-preview": {
"id": "openai/gpt-4o-search-preview",
"name": "GPT-4o Search Preview",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"openai/gpt-4o:extended": {
"id": "openai/gpt-4o:extended",
"name": "GPT-4o (extended)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-5": {
"id": "openai/gpt-5",
"name": "GPT-5",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5-chat": {
"id": "openai/gpt-5-chat",
"name": "GPT-5 Chat",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-5-codex": {
"id": "openai/gpt-5-codex",
"name": "GPT-5 Codex",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5-image": {
"id": "openai/gpt-5-image",
"name": "GPT-5 Image",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 10,
"output": 10,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5-image-mini": {
"id": "openai/gpt-5-image-mini",
"name": "GPT-5 Image Mini",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5-mini": {
"id": "openai/gpt-5-mini",
"name": "GPT-5 Mini",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 2,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5-nano": {
"id": "openai/gpt-5-nano",
"name": "GPT-5 Nano",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.05,
"output": 0.4,
"cacheRead": 0.005,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5-pro": {
"id": "openai/gpt-5-pro",
"name": "GPT-5 Pro",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 120,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5.1": {
"id": "openai/gpt-5.1",
"name": "GPT-5.1",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5.1-chat": {
"id": "openai/gpt-5.1-chat",
"name": "GPT-5.1 Chat",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-5.1-codex": {
"id": "openai/gpt-5.1-codex",
"name": "GPT-5.1-Codex",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5.1-codex-max": {
"id": "openai/gpt-5.1-codex-max",
"name": "GPT-5.1-Codex-Max",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5.1-codex-mini": {
"id": "openai/gpt-5.1-codex-mini",
"name": "GPT-5.1-Codex-Mini",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 2,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"medium",
"high"
]
}
},
"openai/gpt-5.2": {
"id": "openai/gpt-5.2",
"name": "GPT-5.2",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.2-chat": {
"id": "openai/gpt-5.2-chat",
"name": "GPT-5.2 Chat",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-5.2-codex": {
"id": "openai/gpt-5.2-codex",
"name": "GPT-5.2-Codex",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.2-pro": {
"id": "openai/gpt-5.2-pro",
"name": "GPT-5.2 Pro",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 21,
"output": 168,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.3-chat": {
"id": "openai/gpt-5.3-chat",
"name": "GPT-5.3 Chat",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-5.3-codex": {
"id": "openai/gpt-5.3-codex",
"name": "GPT-5.3-Codex",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.4": {
"id": "openai/gpt-5.4",
"name": "GPT-5.4",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.4-image-2": {
"id": "openai/gpt-5.4-image-2",
"name": "GPT-5.4 Image 2",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"openai/gpt-5.4-mini": {
"id": "openai/gpt-5.4-mini",
"name": "GPT-5.4 Mini",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.75,
"output": 4.5,
"cacheRead": 0.075,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.4-nano": {
"id": "openai/gpt-5.4-nano",
"name": "GPT-5.4 Nano",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.2,
"output": 1.25,
"cacheRead": 0.02,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.4-pro": {
"id": "openai/gpt-5.4-pro",
"name": "GPT-5.4 Pro",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 30,
"output": 180,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.5": {
"id": "openai/gpt-5.5",
"name": "GPT-5.5",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 30,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
},
"contextPromotionTarget": "kilo/openai/gpt-5.4"
},
"openai/gpt-5.5-pro": {
"id": "openai/gpt-5.5-pro",
"name": "GPT-5.5 Pro",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 30,
"output": 180,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
},
"contextPromotionTarget": "kilo/openai/gpt-5.4"
},
"openai/gpt-audio": {
"id": "openai/gpt-audio",
"name": "GPT Audio",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"openai/gpt-audio-mini": {
"id": "openai/gpt-audio-mini",
"name": "GPT Audio Mini",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"openai/gpt-chat-latest": {
"id": "openai/gpt-chat-latest",
"name": "GPT Chat Latest",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 30,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-oss-120b": {
"id": "openai/gpt-oss-120b",
"name": "gpt-oss-120b",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.039,
"output": 0.19,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 26215,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
]
}
},
"openai/gpt-oss-120b:exacto": {
"id": "openai/gpt-oss-120b:exacto",
"name": "gpt-oss-120b (exacto)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 40960
},
"openai/gpt-oss-20b": {
"id": "openai/gpt-oss-20b",
"name": "gpt-oss-20b",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.03,
"output": 0.14,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 26215,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
]
}
},
"openai/gpt-oss-safeguard-20b": {
"id": "openai/gpt-oss-safeguard-20b",
"name": "gpt-oss-safeguard-20b",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.075,
"output": 0.3,
"cacheRead": 0.037,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
]
}
},
"openai/o1": {
"id": "openai/o1",
"name": "o1",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 60,
"cacheRead": 7.5,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000
},
"openai/o1-pro": {
"id": "openai/o1-pro",
"name": "o1-pro",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000
},
"openai/o3": {
"id": "openai/o3",
"name": "o3",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 8,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"openai/o3-deep-research": {
"id": "openai/o3-deep-research",
"name": "o3 Deep Research",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 10,
"output": 40,
"cacheRead": 2.5,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"openai/o3-mini": {
"id": "openai/o3-mini",
"name": "o3 Mini",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 1.1,
"output": 4.4,
"cacheRead": 0.55,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000
},
"openai/o3-mini-high": {
"id": "openai/o3-mini-high",
"name": "o3 Mini High",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 1.1,
"output": 4.4,
"cacheRead": 0.55,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000
},
"openai/o3-pro": {
"id": "openai/o3-pro",
"name": "o3 Pro",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 20,
"output": 80,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"openai/o4-mini": {
"id": "openai/o4-mini",
"name": "o4 Mini",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.1,
"output": 4.4,
"cacheRead": 0.275,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"openai/o4-mini-deep-research": {
"id": "openai/o4-mini-deep-research",
"name": "o4 Mini Deep Research",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 8,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"openai/o4-mini-high": {
"id": "openai/o4-mini-high",
"name": "o4 Mini High",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.1,
"output": 4.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"opengvlab/internvl3-78b": {
"id": "opengvlab/internvl3-78b",
"name": "InternVL3 78B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"openrouter/auto": {
"id": "openrouter/auto",
"name": "Auto Router",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"openrouter/bodybuilder": {
"id": "openrouter/bodybuilder",
"name": "Body Builder (beta)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"openrouter/elephant-alpha": {
"id": "openrouter/elephant-alpha",
"name": "Elephant (new)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768
},
"openrouter/free": {
"id": "openrouter/free",
"name": "Free Models Router",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"openrouter/fusion": {
"id": "openrouter/fusion",
"name": "Fusion",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"openrouter/healer-alpha": {
"id": "openrouter/healer-alpha",
"name": "Healer Alpha",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32000
},
"openrouter/hunter-alpha": {
"id": "openrouter/hunter-alpha",
"name": "Hunter Alpha",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 32000
},
"openrouter/owl-alpha": {
"id": "openrouter/owl-alpha",
"name": "Owl Alpha",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048756,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"openrouter/pareto-code": {
"id": "openrouter/pareto-code",
"name": "Pareto Code Router",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"perceptron/perceptron-mk1": {
"id": "perceptron/perceptron-mk1",
"name": "Perceptron Mk1",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"perplexity/sonar": {
"id": "perplexity/sonar",
"name": "Sonar",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"perplexity/sonar-deep-research": {
"id": "perplexity/sonar-deep-research",
"name": "Sonar Deep Research",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"perplexity/sonar-pro": {
"id": "perplexity/sonar-pro",
"name": "Sonar Pro",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortRouting": {
"off": "perplexity/sonar-pro",
"minimal": "perplexity/sonar-reasoning-pro",
"low": "perplexity/sonar-reasoning-pro",
"medium": "perplexity/sonar-reasoning-pro",
"high": "perplexity/sonar-reasoning-pro",
"xhigh": "perplexity/sonar-reasoning-pro"
}
},
"compat": {
"supportsStore": false,
"supportsDeveloperRole": false,
"supportsMultipleSystemMessages": false,
"supportsReasoningEffort": true,
"supportsReasoningParams": true,
"reasoningEffortMap": {},
"supportsUsageInStreaming": true,
"alwaysSendMaxTokens": false,
"disableReasoningOnForcedToolChoice": false,
"disableReasoningOnToolChoice": false,
"supportsToolChoice": true,
"supportsForcedToolChoice": true,
"maxTokensField": "max_completion_tokens",
"requiresToolResultName": false,
"requiresAssistantAfterToolResult": false,
"requiresThinkingAsText": false,
"requiresMistralToolIds": false,
"thinkingFormat": "openai",
"reasoningContentField": "reasoning_content",
"requiresReasoningContentForToolCalls": false,
"allowsSyntheticReasoningContentForToolCalls": true,
"requiresAssistantContentForToolCalls": false,
"isOpenRouterHost": false,
"isVercelGatewayHost": false,
"supportsStrictMode": false,
"toolStrictMode": "mixed"
}
},
"perplexity/sonar-pro-search": {
"id": "perplexity/sonar-pro-search",
"name": "Sonar Pro Search",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"poolside/laguna-m.1:free": {
"id": "poolside/laguna-m.1:free",
"name": "Laguna M.1 (free)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"poolside/laguna-xs.2:free": {
"id": "poolside/laguna-xs.2:free",
"name": "Laguna XS.2 (free)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"prime-intellect/intellect-3": {
"id": "prime-intellect/intellect-3",
"name": "INTELLECT-3",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.2,
"output": 1.1,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"qwen/qwen-2.5-72b-instruct": {
"id": "qwen/qwen-2.5-72b-instruct",
"name": "Qwen2.5 72B Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.12,
"output": 0.39,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32768,
"maxTokens": 16384
},
"qwen/qwen-2.5-7b-instruct": {
"id": "qwen/qwen-2.5-7b-instruct",
"name": "Qwen2.5 7B Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.04,
"output": 0.1,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32768,
"maxTokens": 6554
},
"qwen/qwen-2.5-coder-32b-instruct": {
"id": "qwen/qwen-2.5-coder-32b-instruct",
"name": "Qwen2.5 Coder 32B Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"qwen/qwen-2.5-vl-7b-instruct": {
"id": "qwen/qwen-2.5-vl-7b-instruct",
"name": "Qwen2.5-VL 7B Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"qwen/qwen-max": {
"id": "qwen/qwen-max",
"name": "Qwen-Max",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"qwen/qwen-plus": {
"id": "qwen/qwen-plus",
"name": "Qwen-Plus",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.4,
"output": 1.2,
"cacheRead": 0.08,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 32768
},
"qwen/qwen-plus-2025-07-28": {
"id": "qwen/qwen-plus-2025-07-28",
"name": "Qwen Plus 0728",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.26,
"output": 0.78,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 32768
},
"qwen/qwen-plus-2025-07-28:thinking": {
"id": "qwen/qwen-plus-2025-07-28:thinking",
"name": "Qwen Plus 0728 (thinking)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.26,
"output": 0.78,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen-turbo": {
"id": "qwen/qwen-turbo",
"name": "Qwen-Turbo",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"qwen/qwen-vl-max": {
"id": "qwen/qwen-vl-max",
"name": "Qwen VL Max",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"qwen/qwen-vl-plus": {
"id": "qwen/qwen-vl-plus",
"name": "Qwen VL Plus",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"qwen/qwen2.5-coder-7b-instruct": {
"id": "qwen/qwen2.5-coder-7b-instruct",
"name": "Qwen2.5 Coder 7b Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"qwen/qwen2.5-vl-32b-instruct": {
"id": "qwen/qwen2.5-vl-32b-instruct",
"name": "Qwen2.5 VL 32B Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"qwen/qwen2.5-vl-72b-instruct": {
"id": "qwen/qwen2.5-vl-72b-instruct",
"name": "Qwen2.5 VL 72B Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"qwen/qwen3-14b": {
"id": "qwen/qwen3-14b",
"name": "Qwen3 14B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.06,
"output": 0.24,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 40960,
"maxTokens": 40960,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3-235b-a22b": {
"id": "qwen/qwen3-235b-a22b",
"name": "Qwen3 235B A22B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.455,
"output": 1.82,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3-235b-a22b-2507": {
"id": "qwen/qwen3-235b-a22b-2507",
"name": "Qwen3 235B A22B Instruct 2507",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.071,
"output": 0.1,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 52429,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3-235b-a22b-thinking-2507": {
"id": "qwen/qwen3-235b-a22b-thinking-2507",
"name": "Qwen3 235B A22B Thinking 2507",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.11,
"output": 0.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"qwen/qwen3-30b-a3b": {
"id": "qwen/qwen3-30b-a3b",
"name": "Qwen3 30B A3B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.08,
"output": 0.28,
"cacheRead": 0.03,
"cacheWrite": 0
},
"contextWindow": 40960,
"maxTokens": 40960,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3-30b-a3b-instruct-2507": {
"id": "qwen/qwen3-30b-a3b-instruct-2507",
"name": "Qwen3 30B A3B Instruct 2507",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.09,
"output": 0.3,
"cacheRead": 0.04,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"qwen/qwen3-30b-a3b-thinking-2507": {
"id": "qwen/qwen3-30b-a3b-thinking-2507",
"name": "Qwen3 30B A3B Thinking 2507",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.051,
"output": 0.34,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32768,
"maxTokens": 6554,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"qwen/qwen3-32b": {
"id": "qwen/qwen3-32b",
"name": "Qwen3 32B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.08,
"output": 0.24,
"cacheRead": 0.04,
"cacheWrite": 0
},
"contextWindow": 40960,
"maxTokens": 40960,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3-8b": {
"id": "qwen/qwen3-8b",
"name": "Qwen3 8B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.05,
"output": 0.4,
"cacheRead": 0.05,
"cacheWrite": 0
},
"contextWindow": 40960,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3-coder": {
"id": "qwen/qwen3-coder",
"name": "Qwen3 Coder 480B A35B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.22,
"output": 1,
"cacheRead": 0.022,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 52429
},
"qwen/qwen3-coder-30b-a3b-instruct": {
"id": "qwen/qwen3-coder-30b-a3b-instruct",
"name": "Qwen3 Coder 30B A3B Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.07,
"output": 0.27,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 160000,
"maxTokens": 32768
},
"qwen/qwen3-coder-flash": {
"id": "qwen/qwen3-coder-flash",
"name": "Qwen3 Coder Flash",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.195,
"output": 0.975,
"cacheRead": 0.06,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65536
},
"qwen/qwen3-coder-next": {
"id": "qwen/qwen3-coder-next",
"name": "Qwen3 Coder Next",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.12,
"output": 0.75,
"cacheRead": 0.035,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536
},
"qwen/qwen3-coder-plus": {
"id": "qwen/qwen3-coder-plus",
"name": "Qwen3 Coder Plus",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.65,
"output": 3.25,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65536
},
"qwen/qwen3-coder:exacto": {
"id": "qwen/qwen3-coder:exacto",
"name": "Qwen3 Coder 480B A35B (exacto)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536
},
"qwen/qwen3-max": {
"id": "qwen/qwen3-max",
"name": "Qwen3 Max",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 1.2,
"output": 6,
"cacheRead": 0.24,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768
},
"qwen/qwen3-max-thinking": {
"id": "qwen/qwen3-max-thinking",
"name": "Qwen3 Max Thinking",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.78,
"output": 3.9,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"qwen/qwen3-next-80b-a3b-instruct": {
"id": "qwen/qwen3-next-80b-a3b-instruct",
"name": "Qwen3 Next 80B A3B Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.09,
"output": 1.1,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 52429
},
"qwen/qwen3-next-80b-a3b-thinking": {
"id": "qwen/qwen3-next-80b-a3b-thinking",
"name": "Qwen3 Next 80B A3B Thinking",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.0975,
"output": 0.78,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"qwen/qwen3-vl-235b-a22b-instruct": {
"id": "qwen/qwen3-vl-235b-a22b-instruct",
"name": "Qwen3 VL 235B A22B Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.2,
"output": 0.88,
"cacheRead": 0.11,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 52429
},
"qwen/qwen3-vl-235b-a22b-thinking": {
"id": "qwen/qwen3-vl-235b-a22b-thinking",
"name": "Qwen3 VL 235B A22B Thinking",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.26,
"output": 2.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"qwen/qwen3-vl-30b-a3b-instruct": {
"id": "qwen/qwen3-vl-30b-a3b-instruct",
"name": "Qwen3 VL 30B A3B Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.13,
"output": 0.52,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768
},
"qwen/qwen3-vl-30b-a3b-thinking": {
"id": "qwen/qwen3-vl-30b-a3b-thinking",
"name": "Qwen3 VL 30B A3B Thinking",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.13,
"output": 1.56,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"qwen/qwen3-vl-32b-instruct": {
"id": "qwen/qwen3-vl-32b-instruct",
"name": "Qwen3 VL 32B Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.104,
"output": 0.416,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768
},
"qwen/qwen3-vl-8b-instruct": {
"id": "qwen/qwen3-vl-8b-instruct",
"name": "Qwen3 VL 8B Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.08,
"output": 0.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768
},
"qwen/qwen3-vl-8b-thinking": {
"id": "qwen/qwen3-vl-8b-thinking",
"name": "Qwen3 VL 8B Thinking",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.117,
"output": 1.365,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"qwen/qwen3.5-122b-a10b": {
"id": "qwen/qwen3.5-122b-a10b",
"name": "Qwen3.5-122B-A10B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.26,
"output": 2.08,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.5-27b": {
"id": "qwen/qwen3.5-27b",
"name": "Qwen3.5-27B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.195,
"output": 1.56,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.5-35b-a3b": {
"id": "qwen/qwen3.5-35b-a3b",
"name": "Qwen3.5-35B-A3B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1625,
"output": 1.3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.5-397b-a17b": {
"id": "qwen/qwen3.5-397b-a17b",
"name": "Qwen3.5 397B A17B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.39,
"output": 2.34,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.5-9b": {
"id": "qwen/qwen3.5-9b",
"name": "Qwen3.5-9B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.05,
"output": 0.15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.5-flash-02-23": {
"id": "qwen/qwen3.5-flash-02-23",
"name": "Qwen3.5-Flash",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1,
"output": 0.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.5-plus-02-15": {
"id": "qwen/qwen3.5-plus-02-15",
"name": "Qwen3.5 Plus 2026-02-15",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.26,
"output": 1.56,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.5-plus-20260420": {
"id": "qwen/qwen3.5-plus-20260420",
"name": "Qwen3.5 Plus 2026-04-20",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.4,
"output": 2.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.6-27b": {
"id": "qwen/qwen3.6-27b",
"name": "Qwen3.6 27B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.325,
"output": 3.25,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.6-35b-a3b": {
"id": "qwen/qwen3.6-35b-a3b",
"name": "Qwen3.6 35B A3B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 65536
},
"qwen/qwen3.6-flash": {
"id": "qwen/qwen3.6-flash",
"name": "Qwen3.6 Flash",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 1.5,
"cacheRead": 0,
"cacheWrite": 0.3125
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.6-max-preview": {
"id": "qwen/qwen3.6-max-preview",
"name": "Qwen3.6 Max Preview",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.04,
"output": 6.24,
"cacheRead": 0,
"cacheWrite": 1.3
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.6-plus": {
"id": "qwen/qwen3.6-plus",
"name": "Qwen3.6 Plus",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.325,
"output": 1.95,
"cacheRead": 0.0325,
"cacheWrite": 0.40625
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.6-plus-preview:free": {
"id": "qwen/qwen3.6-plus-preview:free",
"name": "Qwen3.6 Plus Preview (free)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 32000
},
"qwen/qwen3.6-plus:free": {
"id": "qwen/qwen3.6-plus:free",
"name": "Qwen3.6 Plus (free)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65536
},
"qwen/qwen3.7-max": {
"id": "qwen/qwen3.7-max",
"name": "Qwen3.7 Max",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.625,
"output": 4.875,
"cacheRead": 0.1625,
"cacheWrite": 2.03125
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.7-plus": {
"id": "qwen/qwen3.7-plus",
"name": "Qwen3.7 Plus",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.7-plus:free": {
"id": "qwen/qwen3.7-plus:free",
"name": "Qwen3.7 Plus (free)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65536
},
"qwen/qwq-32b": {
"id": "qwen/qwq-32b",
"name": "QwQ 32B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"raifle/sorcererlm-8x22b": {
"id": "raifle/sorcererlm-8x22b",
"name": "SorcererLM 8x22B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"reka/reka-edge": {
"id": "reka/reka-edge",
"name": "Reka Edge",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 16384,
"maxTokens": 16384
},
"rekaai/reka-edge": {
"id": "rekaai/reka-edge",
"name": "Reka Edge",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1,
"output": 0.1,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 16384,
"maxTokens": 16384
},
"rekaai/reka-flash-3": {
"id": "rekaai/reka-flash-3",
"name": "Reka Flash 3",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"relace/relace-apply-3": {
"id": "relace/relace-apply-3",
"name": "Relace Apply 3",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"relace/relace-search": {
"id": "relace/relace-search",
"name": "Relace Search",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 128000
},
"sao10k/l3-euryale-70b": {
"id": "sao10k/l3-euryale-70b",
"name": "Llama 3 Euryale 70B v2.1",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 1.48,
"output": 1.48,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 8192,
"maxTokens": 8192
},
"sao10k/l3-lunaris-8b": {
"id": "sao10k/l3-lunaris-8b",
"name": "Llama 3 8B Lunaris",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"sao10k/l3.1-70b-hanami-x1": {
"id": "sao10k/l3.1-70b-hanami-x1",
"name": "Llama 3.1 70B Hanami x1",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"sao10k/l3.1-euryale-70b": {
"id": "sao10k/l3.1-euryale-70b",
"name": "Llama 3.1 Euryale 70B v2.2",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.85,
"output": 0.85,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384
},
"sao10k/l3.3-euryale-70b": {
"id": "sao10k/l3.3-euryale-70b",
"name": "Llama 3.3 Euryale 70B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"stealth/claude-opus-4.6": {
"id": "stealth/claude-opus-4.6",
"name": "Claude Opus 4.6",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 4,
"output": 20,
"cacheRead": 0.4,
"cacheWrite": 5
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"stealth/claude-opus-4.7": {
"id": "stealth/claude-opus-4.7",
"name": "Claude Opus 4.7",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 4,
"output": 20,
"cacheRead": 0.4,
"cacheWrite": 5
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"stealth/claude-opus-4.8": {
"id": "stealth/claude-opus-4.8",
"name": "Claude Opus 4.8",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000
},
"stealth/claude-sonnet-4.6": {
"id": "stealth/claude-sonnet-4.6",
"name": "Claude Sonnet 4.6",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.4,
"output": 12,
"cacheRead": 0.24,
"cacheWrite": 3
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"stealth/qwen3.6-plus": {
"id": "stealth/qwen3.6-plus",
"name": "Qwen3.6 Plus",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65536
},
"stepfun/step-3.5-flash": {
"id": "stepfun/step-3.5-flash",
"name": "Step 3.5 Flash",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.1,
"output": 0.3,
"cacheRead": 0.02,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"stepfun/step-3.5-flash:free": {
"id": "stepfun/step-3.5-flash:free",
"name": "Step 3.5 Flash (free)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 16384
},
"stepfun/step-3.7-flash": {
"id": "stepfun/step-3.7-flash",
"name": "Step 3.7 Flash",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"stepfun/step-3.7-flash:free": {
"id": "stepfun/step-3.7-flash:free",
"name": "Step 3.7 Flash (free)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000
},
"switchpoint/router": {
"id": "switchpoint/router",
"name": "Switchpoint Router",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"tencent/hunyuan-a13b-instruct": {
"id": "tencent/hunyuan-a13b-instruct",
"name": "Hunyuan A13B Instruct",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"tencent/hy3-preview": {
"id": "tencent/hy3-preview",
"name": "Hy3 Preview",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.066,
"output": 0.26,
"cacheRead": 0.029,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"tencent/hy3-preview:free": {
"id": "tencent/hy3-preview:free",
"name": "Hy3 preview (free)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 64000
},
"thedrummer/cydonia-24b-v4.1": {
"id": "thedrummer/cydonia-24b-v4.1",
"name": "Cydonia 24B V4.1",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"thedrummer/rocinante-12b": {
"id": "thedrummer/rocinante-12b",
"name": "Rocinante 12B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.17,
"output": 0.43,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32768,
"maxTokens": 32768
},
"thedrummer/skyfall-36b-v2": {
"id": "thedrummer/skyfall-36b-v2",
"name": "Skyfall 36B V2",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"thedrummer/unslopnemo-12b": {
"id": "thedrummer/unslopnemo-12b",
"name": "UnslopNemo 12B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.4,
"output": 0.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32768,
"maxTokens": 32768
},
"tngtech/deepseek-r1t2-chimera": {
"id": "tngtech/deepseek-r1t2-chimera",
"name": "DeepSeek R1T2 Chimera",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 163840
},
"undi95/remm-slerp-l2-13b": {
"id": "undi95/remm-slerp-l2-13b",
"name": "ReMM SLERP 13B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"upstage/solar-pro-3": {
"id": "upstage/solar-pro-3",
"name": "Solar Pro 3",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"writer/palmyra-x5": {
"id": "writer/palmyra-x5",
"name": "Palmyra X5",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"x-ai/grok-3": {
"id": "x-ai/grok-3",
"name": "Grok 3",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192
},
"x-ai/grok-3-beta": {
"id": "x-ai/grok-3-beta",
"name": "Grok 3 Beta",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": null
},
"x-ai/grok-3-mini": {
"id": "x-ai/grok-3-mini",
"name": "Grok 3 Mini",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192
},
"x-ai/grok-3-mini-beta": {
"id": "x-ai/grok-3-mini-beta",
"name": "Grok 3 Mini Beta",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": null
},
"x-ai/grok-4": {
"id": "x-ai/grok-4",
"name": "Grok 4",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"x-ai/grok-4-fast": {
"id": "x-ai/grok-4-fast",
"name": "Grok 4 Fast",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"x-ai/grok-4.1-fast": {
"id": "x-ai/grok-4.1-fast",
"name": "Grok 4.1 Fast",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"x-ai/grok-4.20": {
"id": "x-ai/grok-4.20",
"name": "Grok 4.20",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 6,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 2000000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"x-ai/grok-4.20-beta": {
"id": "x-ai/grok-4.20-beta",
"name": "Grok 4.20 Beta",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": null
},
"x-ai/grok-4.20-multi-agent": {
"id": "x-ai/grok-4.20-multi-agent",
"name": "Grok 4.20 Multi-Agent",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 2000000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"x-ai/grok-4.20-multi-agent-beta": {
"id": "x-ai/grok-4.20-multi-agent-beta",
"name": "Grok 4.20 Multi-Agent Beta",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 2000000
},
"x-ai/grok-4.3": {
"id": "x-ai/grok-4.3",
"name": "Grok 4.3",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 2.5,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 4096,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"x-ai/grok-build-0.1": {
"id": "x-ai/grok-build-0.1",
"name": "Grok Build 0.1",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1,
"output": 2,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"x-ai/grok-code-fast-1": {
"id": "x-ai/grok-code-fast-1",
"name": "Grok Code Fast 1",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"x-ai/grok-code-fast-1:optimized:free": {
"id": "x-ai/grok-code-fast-1:optimized:free",
"name": "Grok Code Fast 1, retiring May 15 (free)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 10000
},
"xiaomi/mimo-v2-flash": {
"id": "xiaomi/mimo-v2-flash",
"name": "MiMo-V2-Flash",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.09,
"output": 0.29,
"cacheRead": 0.045,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"xiaomi/mimo-v2-omni": {
"id": "xiaomi/mimo-v2-omni",
"name": "MiMo-V2-Omni",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.4,
"output": 2,
"cacheRead": 0.08,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"xiaomi/mimo-v2-omni:free": {
"id": "xiaomi/mimo-v2-omni:free",
"name": "MiMo-V2-Omni (free)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 131072
},
"xiaomi/mimo-v2-pro": {
"id": "xiaomi/mimo-v2-pro",
"name": "MiMo-V2-Pro",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 3,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"xiaomi/mimo-v2-pro:free": {
"id": "xiaomi/mimo-v2-pro:free",
"name": "MiMo-V2-Pro (free)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072
},
"xiaomi/mimo-v2.5": {
"id": "xiaomi/mimo-v2.5",
"name": "MiMo-V2.5",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.4,
"output": 2,
"cacheRead": 0.08,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"xiaomi/mimo-v2.5-pro": {
"id": "xiaomi/mimo-v2.5-pro",
"name": "MiMo V2.5 Pro",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 3,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"z-ai/glm-4-32b": {
"id": "z-ai/glm-4-32b",
"name": "GLM 4 32B",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.1,
"output": 0.1,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 32768
},
"z-ai/glm-4.5": {
"id": "z-ai/glm-4.5",
"name": "GLM 4.5",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.2,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 98304,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"z-ai/glm-4.5-air": {
"id": "z-ai/glm-4.5-air",
"name": "GLM 4.5 Air",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.13,
"output": 0.85,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 98304,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"z-ai/glm-4.5v": {
"id": "z-ai/glm-4.5v",
"name": "GLM 4.5V",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.6,
"output": 1.8,
"cacheRead": 0.11,
"cacheWrite": 0
},
"contextWindow": 65536,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"z-ai/glm-4.6": {
"id": "z-ai/glm-4.6",
"name": "GLM 4.6",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.39,
"output": 1.9,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 204800,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"z-ai/glm-4.6:exacto": {
"id": "z-ai/glm-4.6:exacto",
"name": "GLM 4.6 (exacto)",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072
},
"z-ai/glm-4.6v": {
"id": "z-ai/glm-4.6v",
"name": "GLM 4.6V",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 0.9,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"z-ai/glm-4.7": {
"id": "z-ai/glm-4.7",
"name": "GLM 4.7",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.38,
"output": 1.98,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 65535,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"z-ai/glm-4.7-flash": {
"id": "z-ai/glm-4.7-flash",
"name": "GLM 4.7 Flash",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.06,
"output": 0.4,
"cacheRead": 0.01,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 40551,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"z-ai/glm-5": {
"id": "z-ai/glm-5",
"name": "GLM 5",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.72,
"output": 2.3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"z-ai/glm-5-turbo": {
"id": "z-ai/glm-5-turbo",
"name": "GLM 5 Turbo",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.2,
"output": 4,
"cacheRead": 0.24,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"z-ai/glm-5.1": {
"id": "z-ai/glm-5.1",
"name": "GLM 5.1",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.26,
"output": 3.96,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"z-ai/glm-5.2": {
"id": "z-ai/glm-5.2",
"name": "GLM 5.2",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072
},
"z-ai/glm-5v-turbo": {
"id": "z-ai/glm-5v-turbo",
"name": "GLM 5V Turbo",
"api": "openai-completions",
"provider": "kilo",
"baseUrl": "https://api.kilo.ai/api/gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.2,
"output": 4,
"cacheRead": 0.24,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
}
},
"kimi-code": {
"kimi-for-coding": {
"id": "kimi-for-coding",
"name": "Kimi For Coding",
"api": "openai-completions",
"provider": "kimi-code",
"baseUrl": "https://api.kimi.com/coding/v1",
"headers": {
"User-Agent": "KimiCLI/1.0",
"X-Msh-Platform": "kimi_cli"
},
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
},
"compat": {
"thinkingFormat": "zai",
"reasoningContentField": "reasoning_content",
"supportsDeveloperRole": false
}
},
"kimi-k2": {
"id": "kimi-k2",
"name": "Kimi K2",
"api": "openai-completions",
"provider": "kimi-code",
"baseUrl": "https://api.kimi.com/coding/v1",
"headers": {
"User-Agent": "KimiCLI/1.0",
"X-Msh-Platform": "kimi_cli"
},
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"compat": {
"thinkingFormat": "zai",
"reasoningContentField": "reasoning_content",
"supportsDeveloperRole": false
}
},
"kimi-k2-turbo-preview": {
"id": "kimi-k2-turbo-preview",
"name": "Kimi K2 Turbo",
"api": "openai-completions",
"provider": "kimi-code",
"baseUrl": "https://api.kimi.com/coding/v1",
"headers": {
"User-Agent": "KimiCLI/1.0",
"X-Msh-Platform": "kimi_cli"
},
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32000,
"compat": {
"thinkingFormat": "zai",
"reasoningContentField": "reasoning_content",
"supportsDeveloperRole": false
}
},
"kimi-k2.5": {
"id": "kimi-k2.5",
"name": "Kimi K2.5",
"api": "openai-completions",
"provider": "kimi-code",
"baseUrl": "https://api.kimi.com/coding/v1",
"headers": {
"User-Agent": "KimiCLI/1.0",
"X-Msh-Platform": "kimi_cli"
},
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
},
"compat": {
"thinkingFormat": "zai",
"reasoningContentField": "reasoning_content",
"supportsDeveloperRole": false
}
}
},
"minimax": {
"MiniMax-M2": {
"id": "MiniMax-M2",
"name": "MiniMax-M2",
"api": "anthropic-messages",
"provider": "minimax",
"baseUrl": "https://api.minimax.io/anthropic",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 196608,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"MiniMax-M2.1": {
"id": "MiniMax-M2.1",
"name": "MiniMax-M2.1",
"api": "anthropic-messages",
"provider": "minimax",
"baseUrl": "https://api.minimax.io/anthropic",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"MiniMax-M2.5": {
"id": "MiniMax-M2.5",
"name": "MiniMax-M2.5",
"api": "anthropic-messages",
"provider": "minimax",
"baseUrl": "https://api.minimax.io/anthropic",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.03,
"cacheWrite": 0.375
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"MiniMax-M2.5-highspeed": {
"id": "MiniMax-M2.5-highspeed",
"name": "MiniMax-M2.5-highspeed",
"api": "anthropic-messages",
"provider": "minimax",
"baseUrl": "https://api.minimax.io/anthropic",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.4,
"cacheRead": 0.06,
"cacheWrite": 0.375
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"MiniMax-M2.5-lightning": {
"id": "MiniMax-M2.5-lightning",
"name": "MiniMax M2.5 Lightning",
"api": "anthropic-messages",
"provider": "minimax",
"baseUrl": "https://api.minimax.io/anthropic",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 2.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 32000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"MiniMax-M2.7": {
"id": "MiniMax-M2.7",
"name": "MiniMax-M2.7",
"api": "anthropic-messages",
"provider": "minimax",
"baseUrl": "https://api.minimax.io/anthropic",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.06,
"cacheWrite": 0.375
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"MiniMax-M2.7-highspeed": {
"id": "MiniMax-M2.7-highspeed",
"name": "MiniMax-M2.7-highspeed",
"api": "anthropic-messages",
"provider": "minimax",
"baseUrl": "https://api.minimax.io/anthropic",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.4,
"cacheRead": 0.06,
"cacheWrite": 0.375
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"MiniMax-M3": {
"id": "MiniMax-M3",
"name": "MiniMax-M3",
"api": "anthropic-messages",
"provider": "minimax",
"baseUrl": "https://api.minimax.io/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.6,
"output": 2.4,
"cacheRead": 0.12,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
}
},
"minimax-cn": {
"MiniMax-M2": {
"id": "MiniMax-M2",
"name": "MiniMax-M2",
"api": "anthropic-messages",
"provider": "minimax-cn",
"baseUrl": "https://api.minimaxi.com/anthropic",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 196608,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"MiniMax-M2.1": {
"id": "MiniMax-M2.1",
"name": "MiniMax-M2.1",
"api": "anthropic-messages",
"provider": "minimax-cn",
"baseUrl": "https://api.minimaxi.com/anthropic",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"MiniMax-M2.5": {
"id": "MiniMax-M2.5",
"name": "MiniMax-M2.5",
"api": "anthropic-messages",
"provider": "minimax-cn",
"baseUrl": "https://api.minimaxi.com/anthropic",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.03,
"cacheWrite": 0.375
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"MiniMax-M2.5-highspeed": {
"id": "MiniMax-M2.5-highspeed",
"name": "MiniMax-M2.5-highspeed",
"api": "anthropic-messages",
"provider": "minimax-cn",
"baseUrl": "https://api.minimaxi.com/anthropic",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.4,
"cacheRead": 0.06,
"cacheWrite": 0.375
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"MiniMax-M2.5-lightning": {
"id": "MiniMax-M2.5-lightning",
"name": "MiniMax M2.5 Lightning (CN)",
"api": "anthropic-messages",
"provider": "minimax-cn",
"baseUrl": "https://api.minimaxi.com/anthropic",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 2.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 32000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"MiniMax-M2.7": {
"id": "MiniMax-M2.7",
"name": "MiniMax-M2.7",
"api": "anthropic-messages",
"provider": "minimax-cn",
"baseUrl": "https://api.minimaxi.com/anthropic",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.06,
"cacheWrite": 0.375
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"MiniMax-M2.7-highspeed": {
"id": "MiniMax-M2.7-highspeed",
"name": "MiniMax-M2.7-highspeed",
"api": "anthropic-messages",
"provider": "minimax-cn",
"baseUrl": "https://api.minimaxi.com/anthropic",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.4,
"cacheRead": 0.06,
"cacheWrite": 0.375
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"MiniMax-M3": {
"id": "MiniMax-M3",
"name": "MiniMax-M3",
"api": "anthropic-messages",
"provider": "minimax-cn",
"baseUrl": "https://api.minimaxi.com/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.6,
"output": 2.4,
"cacheRead": 0.12,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
}
},
"minimax-code": {
"MiniMax-M2": {
"id": "MiniMax-M2",
"name": "MiniMax-M2",
"api": "openai-completions",
"provider": "minimax-code",
"baseUrl": "https://api.minimax.io/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 196608,
"maxTokens": 128000,
"compat": {
"supportsStore": false,
"supportsDeveloperRole": false,
"supportsReasoningEffort": false,
"reasoningContentField": "reasoning_content"
},
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"MiniMax-M2.1": {
"id": "MiniMax-M2.1",
"name": "MiniMax-M2.1",
"api": "openai-completions",
"provider": "minimax-code",
"baseUrl": "https://api.minimax.io/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"compat": {
"supportsStore": false,
"supportsDeveloperRole": false,
"supportsReasoningEffort": false,
"reasoningContentField": "reasoning_content"
},
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"MiniMax-M2.1-lightning": {
"id": "MiniMax-M2.1-lightning",
"name": "MiniMax M2.1 Lightning (Coding Plan)",
"api": "openai-completions",
"provider": "minimax-code",
"baseUrl": "https://api.minimax.io/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"compat": {
"supportsDeveloperRole": false,
"supportsReasoningEffort": false,
"reasoningContentField": "reasoning_content",
"supportsStore": false
},
"contextWindow": 1000000,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"MiniMax-M2.5": {
"id": "MiniMax-M2.5",
"name": "MiniMax-M2.5",
"api": "openai-completions",
"provider": "minimax-code",
"baseUrl": "https://api.minimax.io/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"compat": {
"supportsStore": false,
"supportsDeveloperRole": false,
"supportsReasoningEffort": false,
"reasoningContentField": "reasoning_content"
},
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"MiniMax-M2.5-highspeed": {
"id": "MiniMax-M2.5-highspeed",
"name": "MiniMax-M2.5-highspeed",
"api": "openai-completions",
"provider": "minimax-code",
"baseUrl": "https://api.minimax.io/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"compat": {
"supportsStore": false,
"supportsDeveloperRole": false,
"supportsReasoningEffort": false,
"reasoningContentField": "reasoning_content"
},
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"MiniMax-M2.5-lightning": {
"id": "MiniMax-M2.5-lightning",
"name": "MiniMax M2.5 Lightning (Coding Plan)",
"api": "openai-completions",
"provider": "minimax-code",
"baseUrl": "https://api.minimax.io/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"compat": {
"supportsDeveloperRole": false,
"supportsReasoningEffort": false,
"reasoningContentField": "reasoning_content",
"supportsStore": false
},
"contextWindow": 204800,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"MiniMax-M2.7": {
"id": "MiniMax-M2.7",
"name": "MiniMax-M2.7",
"api": "openai-completions",
"provider": "minimax-code",
"baseUrl": "https://api.minimax.io/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"compat": {
"supportsStore": false,
"supportsDeveloperRole": false,
"supportsReasoningEffort": false,
"reasoningContentField": "reasoning_content"
},
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"MiniMax-M2.7-highspeed": {
"id": "MiniMax-M2.7-highspeed",
"name": "MiniMax-M2.7-highspeed",
"api": "openai-completions",
"provider": "minimax-code",
"baseUrl": "https://api.minimax.io/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"compat": {
"supportsStore": false,
"supportsDeveloperRole": false,
"supportsReasoningEffort": false,
"reasoningContentField": "reasoning_content"
},
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"MiniMax-M3": {
"id": "MiniMax-M3",
"name": "MiniMax-M3",
"api": "openai-completions",
"provider": "minimax-code",
"baseUrl": "https://api.minimax.io/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 512000,
"maxTokens": 128000,
"compat": {
"supportsStore": false,
"supportsDeveloperRole": false,
"supportsReasoningEffort": false,
"reasoningContentField": "reasoning_content"
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
}
},
"minimax-code-cn": {
"MiniMax-M2": {
"id": "MiniMax-M2",
"name": "MiniMax-M2",
"api": "openai-completions",
"provider": "minimax-code-cn",
"baseUrl": "https://api.minimaxi.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 196608,
"maxTokens": 128000,
"compat": {
"supportsStore": false,
"supportsDeveloperRole": false,
"supportsReasoningEffort": false,
"reasoningContentField": "reasoning_content"
},
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"MiniMax-M2.1": {
"id": "MiniMax-M2.1",
"name": "MiniMax-M2.1",
"api": "openai-completions",
"provider": "minimax-code-cn",
"baseUrl": "https://api.minimaxi.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"compat": {
"supportsStore": false,
"supportsDeveloperRole": false,
"supportsReasoningEffort": false,
"reasoningContentField": "reasoning_content"
},
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"MiniMax-M2.1-lightning": {
"id": "MiniMax-M2.1-lightning",
"name": "MiniMax M2.1 Lightning (Coding Plan CN)",
"api": "openai-completions",
"provider": "minimax-code-cn",
"baseUrl": "https://api.minimaxi.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"compat": {
"supportsDeveloperRole": false,
"supportsReasoningEffort": false,
"reasoningContentField": "reasoning_content",
"supportsStore": false
},
"contextWindow": 1000000,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"MiniMax-M2.5": {
"id": "MiniMax-M2.5",
"name": "MiniMax-M2.5",
"api": "openai-completions",
"provider": "minimax-code-cn",
"baseUrl": "https://api.minimaxi.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"compat": {
"supportsStore": false,
"supportsDeveloperRole": false,
"supportsReasoningEffort": false,
"reasoningContentField": "reasoning_content"
},
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"MiniMax-M2.5-highspeed": {
"id": "MiniMax-M2.5-highspeed",
"name": "MiniMax-M2.5-highspeed",
"api": "openai-completions",
"provider": "minimax-code-cn",
"baseUrl": "https://api.minimaxi.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"compat": {
"supportsStore": false,
"supportsDeveloperRole": false,
"supportsReasoningEffort": false,
"reasoningContentField": "reasoning_content"
},
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"MiniMax-M2.5-lightning": {
"id": "MiniMax-M2.5-lightning",
"name": "MiniMax M2.5 Lightning (Coding Plan CN)",
"api": "openai-completions",
"provider": "minimax-code-cn",
"baseUrl": "https://api.minimaxi.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"compat": {
"supportsDeveloperRole": false,
"supportsReasoningEffort": false,
"reasoningContentField": "reasoning_content",
"supportsStore": false
},
"contextWindow": 204800,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"MiniMax-M2.7": {
"id": "MiniMax-M2.7",
"name": "MiniMax-M2.7",
"api": "openai-completions",
"provider": "minimax-code-cn",
"baseUrl": "https://api.minimaxi.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"compat": {
"supportsStore": false,
"supportsDeveloperRole": false,
"supportsReasoningEffort": false,
"reasoningContentField": "reasoning_content"
},
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"MiniMax-M2.7-highspeed": {
"id": "MiniMax-M2.7-highspeed",
"name": "MiniMax-M2.7-highspeed",
"api": "openai-completions",
"provider": "minimax-code-cn",
"baseUrl": "https://api.minimaxi.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"compat": {
"supportsStore": false,
"supportsDeveloperRole": false,
"supportsReasoningEffort": false,
"reasoningContentField": "reasoning_content"
},
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"MiniMax-M3": {
"id": "MiniMax-M3",
"name": "MiniMax-M3",
"api": "openai-completions",
"provider": "minimax-code-cn",
"baseUrl": "https://api.minimaxi.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 512000,
"maxTokens": 128000,
"compat": {
"supportsStore": false,
"supportsDeveloperRole": false,
"supportsReasoningEffort": false,
"reasoningContentField": "reasoning_content"
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
}
},
"mistral": {
"codestral-latest": {
"id": "codestral-latest",
"name": "Codestral",
"api": "openai-completions",
"provider": "mistral",
"baseUrl": "https://api.mistral.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 0.9,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 4096
},
"devstral-2512": {
"id": "devstral-2512",
"name": "Devstral 2",
"api": "openai-completions",
"provider": "mistral",
"baseUrl": "https://api.mistral.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.4,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"devstral-latest": {
"id": "devstral-latest",
"name": "Devstral 2",
"api": "openai-completions",
"provider": "mistral",
"baseUrl": "https://api.mistral.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.4,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"devstral-medium-2507": {
"id": "devstral-medium-2507",
"name": "Devstral Medium",
"api": "openai-completions",
"provider": "mistral",
"baseUrl": "https://api.mistral.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.4,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 128000
},
"devstral-medium-latest": {
"id": "devstral-medium-latest",
"name": "Devstral 2",
"api": "openai-completions",
"provider": "mistral",
"baseUrl": "https://api.mistral.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.4,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"devstral-small-2505": {
"id": "devstral-small-2505",
"name": "Devstral Small 2505",
"api": "openai-completions",
"provider": "mistral",
"baseUrl": "https://api.mistral.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.1,
"output": 0.3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 128000
},
"devstral-small-2507": {
"id": "devstral-small-2507",
"name": "Devstral Small",
"api": "openai-completions",
"provider": "mistral",
"baseUrl": "https://api.mistral.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.1,
"output": 0.3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 128000
},
"labs-devstral-small-2512": {
"id": "labs-devstral-small-2512",
"name": "Devstral Small 2",
"api": "openai-completions",
"provider": "mistral",
"baseUrl": "https://api.mistral.ai/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000
},
"magistral-medium-latest": {
"id": "magistral-medium-latest",
"name": "Magistral Medium",
"api": "openai-completions",
"provider": "mistral",
"baseUrl": "https://api.mistral.ai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 2,
"output": 5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"magistral-small": {
"id": "magistral-small",
"name": "Magistral Small",
"api": "openai-completions",
"provider": "mistral",
"baseUrl": "https://api.mistral.ai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.5,
"output": 1.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"ministral-3b-latest": {
"id": "ministral-3b-latest",
"name": "Ministral 3B",
"api": "openai-completions",
"provider": "mistral",
"baseUrl": "https://api.mistral.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.04,
"output": 0.04,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 128000
},
"ministral-8b-latest": {
"id": "ministral-8b-latest",
"name": "Ministral 8B",
"api": "openai-completions",
"provider": "mistral",
"baseUrl": "https://api.mistral.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.1,
"output": 0.1,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 128000
},
"mistral-large-2411": {
"id": "mistral-large-2411",
"name": "Mistral Large 2.1",
"api": "openai-completions",
"provider": "mistral",
"baseUrl": "https://api.mistral.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 2,
"output": 6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384
},
"mistral-large-2512": {
"id": "mistral-large-2512",
"name": "Mistral Large 3",
"api": "openai-completions",
"provider": "mistral",
"baseUrl": "https://api.mistral.ai/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.5,
"output": 1.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"mistral-large-latest": {
"id": "mistral-large-latest",
"name": "Mistral Large",
"api": "openai-completions",
"provider": "mistral",
"baseUrl": "https://api.mistral.ai/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.5,
"output": 1.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"mistral-medium-2505": {
"id": "mistral-medium-2505",
"name": "Mistral Medium 3",
"api": "openai-completions",
"provider": "mistral",
"baseUrl": "https://api.mistral.ai/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.4,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072
},
"mistral-medium-2508": {
"id": "mistral-medium-2508",
"name": "Mistral Medium 3.1",
"api": "openai-completions",
"provider": "mistral",
"baseUrl": "https://api.mistral.ai/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.4,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"mistral-medium-2604": {
"id": "mistral-medium-2604",
"name": "Mistral Medium 3.5",
"api": "openai-completions",
"provider": "mistral",
"baseUrl": "https://api.mistral.ai/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.5,
"output": 7.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"mistral-medium-latest": {
"id": "mistral-medium-latest",
"name": "Mistral Medium",
"api": "openai-completions",
"provider": "mistral",
"baseUrl": "https://api.mistral.ai/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.4,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"mistral-nemo": {
"id": "mistral-nemo",
"name": "Mistral Nemo",
"api": "openai-completions",
"provider": "mistral",
"baseUrl": "https://api.mistral.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 128000
},
"mistral-small-2506": {
"id": "mistral-small-2506",
"name": "Mistral Small 3.2",
"api": "openai-completions",
"provider": "mistral",
"baseUrl": "https://api.mistral.ai/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1,
"output": 0.3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"mistral-small-2603": {
"id": "mistral-small-2603",
"name": "Mistral Small 4",
"api": "openai-completions",
"provider": "mistral",
"baseUrl": "https://api.mistral.ai/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"mistral-small-latest": {
"id": "mistral-small-latest",
"name": "Mistral Small",
"api": "openai-completions",
"provider": "mistral",
"baseUrl": "https://api.mistral.ai/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"open-mistral-7b": {
"id": "open-mistral-7b",
"name": "Mistral 7B",
"api": "openai-completions",
"provider": "mistral",
"baseUrl": "https://api.mistral.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.25,
"output": 0.25,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 8000,
"maxTokens": 8000
},
"open-mistral-nemo": {
"id": "open-mistral-nemo",
"name": "Open Mistral Nemo",
"api": "openai-completions",
"provider": "mistral",
"baseUrl": "https://api.mistral.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 128000
},
"open-mixtral-8x22b": {
"id": "open-mixtral-8x22b",
"name": "Mixtral 8x22B",
"api": "openai-completions",
"provider": "mistral",
"baseUrl": "https://api.mistral.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 2,
"output": 6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 64000,
"maxTokens": 64000
},
"open-mixtral-8x7b": {
"id": "open-mixtral-8x7b",
"name": "Mixtral 8x7B",
"api": "openai-completions",
"provider": "mistral",
"baseUrl": "https://api.mistral.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.7,
"output": 0.7,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32000,
"maxTokens": 32000
},
"pixtral-12b": {
"id": "pixtral-12b",
"name": "Pixtral 12B",
"api": "openai-completions",
"provider": "mistral",
"baseUrl": "https://api.mistral.ai/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 0.15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 128000
},
"pixtral-large-latest": {
"id": "pixtral-large-latest",
"name": "Pixtral Large",
"api": "openai-completions",
"provider": "mistral",
"baseUrl": "https://api.mistral.ai/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 128000
}
},
"moonshot": {
"kimi-k2-0711-preview": {
"id": "kimi-k2-0711-preview",
"name": "Kimi K2 0711",
"api": "openai-completions",
"provider": "moonshot",
"baseUrl": "https://api.moonshot.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.5,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384
},
"kimi-k2-0905-preview": {
"id": "kimi-k2-0905-preview",
"name": "Kimi K2 0905",
"api": "openai-completions",
"provider": "moonshot",
"baseUrl": "https://api.moonshot.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.5,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"kimi-k2-thinking": {
"id": "kimi-k2-thinking",
"name": "Kimi K2 Thinking",
"api": "openai-completions",
"provider": "moonshot",
"baseUrl": "https://api.moonshot.ai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.5,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"kimi-k2-thinking-turbo": {
"id": "kimi-k2-thinking-turbo",
"name": "Kimi K2 Thinking Turbo",
"api": "openai-completions",
"provider": "moonshot",
"baseUrl": "https://api.moonshot.ai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.15,
"output": 8,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"kimi-k2-turbo-preview": {
"id": "kimi-k2-turbo-preview",
"name": "Kimi K2 Turbo",
"api": "openai-completions",
"provider": "moonshot",
"baseUrl": "https://api.moonshot.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 2.4,
"output": 10,
"cacheRead": 0.6,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"kimi-k2.5": {
"id": "kimi-k2.5",
"name": "Kimi K2.5",
"api": "openai-completions",
"provider": "moonshot",
"baseUrl": "https://api.moonshot.ai/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.6,
"output": 3,
"cacheRead": 0.1,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"kimi-k2.6": {
"id": "kimi-k2.6",
"name": "Kimi K2.6",
"api": "openai-completions",
"provider": "moonshot",
"baseUrl": "https://api.moonshot.ai/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.95,
"output": 4,
"cacheRead": 0.16,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"kimi-k2.7-code": {
"id": "kimi-k2.7-code",
"name": "Kimi K2.7 Code",
"api": "openai-completions",
"provider": "moonshot",
"baseUrl": "https://api.moonshot.ai/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.95,
"output": 4,
"cacheRead": 0.19,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"kimi-k2.7-code-highspeed": {
"id": "kimi-k2.7-code-highspeed",
"name": "Kimi K2.7 Code HighSpeed",
"api": "openai-completions",
"provider": "moonshot",
"baseUrl": "https://api.moonshot.ai/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.9,
"output": 8,
"cacheRead": 0.38,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
}
},
"nanogpt": {
"abacusai/Dracarys-72B-Instruct": {
"id": "abacusai/Dracarys-72B-Instruct",
"name": "abacusai/Dracarys-72B-Instruct",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aion-labs/aion-1.0": {
"id": "aion-labs/aion-1.0",
"name": "aion-labs/aion-1.0",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aion-labs/aion-1.0-mini": {
"id": "aion-labs/aion-1.0-mini",
"name": "aion-labs/aion-1.0-mini",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aion-labs/aion-2.0": {
"id": "aion-labs/aion-2.0",
"name": "aion-labs/aion-2.0",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aion-labs/aion-2.5": {
"id": "aion-labs/aion-2.5",
"name": "aion-labs/aion-2.5",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aion-labs/aion-rp-llama-3.1-8b": {
"id": "aion-labs/aion-rp-llama-3.1-8b",
"name": "aion-labs/aion-rp-llama-3.1-8b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Alibaba-NLP/Tongyi-DeepResearch-30B-A3B": {
"id": "Alibaba-NLP/Tongyi-DeepResearch-30B-A3B",
"name": "Alibaba-NLP/Tongyi-DeepResearch-30B-A3B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"alibaba/qwen3.6-27b": {
"id": "alibaba/qwen3.6-27b",
"name": "alibaba/qwen3.6-27b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262140,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"alibaba/qwen3.6-flash": {
"id": "alibaba/qwen3.6-flash",
"name": "alibaba/qwen3.6-flash",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65536
},
"allenai/molmo-2-8b": {
"id": "allenai/molmo-2-8b",
"name": "allenai/molmo-2-8b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"allenai/olmo-3-32b-think": {
"id": "allenai/olmo-3-32b-think",
"name": "allenai/olmo-3-32b-think",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"allenai/olmo-3.1-32b-instruct": {
"id": "allenai/olmo-3.1-32b-instruct",
"name": "Olmo 3.1 32B Instruct",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.19999999999999998,
"output": 0.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"allenai/olmo-3.1-32b-think": {
"id": "allenai/olmo-3.1-32b-think",
"name": "allenai/olmo-3.1-32b-think",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"amazon/nova-2-lite-v1": {
"id": "amazon/nova-2-lite-v1",
"name": "Nova 2 Lite",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 2.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65535,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"amazon/nova-lite-v1": {
"id": "amazon/nova-lite-v1",
"name": "Nova Lite 1.0",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.06,
"output": 0.24,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 300000,
"maxTokens": 5120,
"compat": {
"supportsToolChoice": false
}
},
"amazon/nova-micro-v1": {
"id": "amazon/nova-micro-v1",
"name": "Nova Micro 1.0",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.035,
"output": 0.14,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 5120,
"compat": {
"supportsToolChoice": false
}
},
"amazon/nova-pro-v1": {
"id": "amazon/nova-pro-v1",
"name": "Nova Pro 1.0",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.7999999999999999,
"output": 3.1999999999999997,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 300000,
"maxTokens": 5120,
"compat": {
"supportsToolChoice": false
}
},
"anthracite-org/magnum-v2-72b": {
"id": "anthracite-org/magnum-v2-72b",
"name": "anthracite-org/magnum-v2-72b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"anthracite-org/magnum-v4-72b": {
"id": "anthracite-org/magnum-v4-72b",
"name": "anthracite-org/magnum-v4-72b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"anthropic/claude-fable-5": {
"id": "anthropic/claude-fable-5",
"name": "Claude Fable 5",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 10,
"output": 50,
"cacheRead": 1,
"cacheWrite": 12.5
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-fable-latest": {
"id": "anthropic/claude-fable-latest",
"name": "anthropic/claude-fable-latest",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"anthropic/claude-haiku-latest": {
"id": "anthropic/claude-haiku-latest",
"name": "Claude Haiku Latest",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1,
"output": 5,
"cacheRead": 0.1,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-opus-4.6": {
"id": "anthropic/claude-opus-4.6",
"name": "Claude 4.6 Opus",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 4.998,
"output": 25.007,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-opus-4.6:thinking": {
"id": "anthropic/claude-opus-4.6:thinking",
"name": "Claude 4.6 Opus Thinking",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 4.998,
"output": 25.007,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-opus-4.6:thinking:low": {
"id": "anthropic/claude-opus-4.6:thinking:low",
"name": "Claude 4.6 Opus Thinking Low",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 4.998,
"output": 25.007,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-opus-4.6:thinking:max": {
"id": "anthropic/claude-opus-4.6:thinking:max",
"name": "Claude 4.6 Opus Thinking Max",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 4.998,
"output": 25.007,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-opus-4.6:thinking:medium": {
"id": "anthropic/claude-opus-4.6:thinking:medium",
"name": "Claude 4.6 Opus Thinking Medium",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 4.998,
"output": 25.007,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-opus-4.7": {
"id": "anthropic/claude-opus-4.7",
"name": "Claude 4.7 Opus",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 4.998,
"output": 25.007,
"cacheRead": 0.4998,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-opus-4.7:thinking": {
"id": "anthropic/claude-opus-4.7:thinking",
"name": "Claude 4.7 Opus Thinking",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 4.998,
"output": 25.007,
"cacheRead": 0.4998,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-opus-4.8": {
"id": "anthropic/claude-opus-4.8",
"name": "Claude Opus 4.8",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 4.998,
"output": 25.007,
"cacheRead": 0.4998,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-opus-4.8:thinking": {
"id": "anthropic/claude-opus-4.8:thinking",
"name": "Claude Opus 4.8 Thinking",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 4.998,
"output": 25.007,
"cacheRead": 0.4998,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-opus-latest": {
"id": "anthropic/claude-opus-latest",
"name": "Claude Opus Latest",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 4.998,
"output": 25.007,
"cacheRead": 0.4998,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-sonnet-4.6": {
"id": "anthropic/claude-sonnet-4.6",
"name": "Claude Sonnet 4.6",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2.992,
"output": 14.993999999999998,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000
},
"anthropic/claude-sonnet-4.6:thinking": {
"id": "anthropic/claude-sonnet-4.6:thinking",
"name": "Claude Sonnet 4.6 Thinking",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.992,
"output": 14.993999999999998,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-sonnet-latest": {
"id": "anthropic/claude-sonnet-latest",
"name": "Claude Sonnet Latest",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.992,
"output": 14.994,
"cacheRead": 0.2992,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"arcee-ai/trinity-large": {
"id": "arcee-ai/trinity-large",
"name": "arcee-ai/trinity-large",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 80000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortRouting": {
"off": "arcee-ai/trinity-large",
"minimal": "arcee-ai/trinity-large-thinking",
"low": "arcee-ai/trinity-large-thinking",
"medium": "arcee-ai/trinity-large-thinking",
"high": "arcee-ai/trinity-large-thinking",
"xhigh": "arcee-ai/trinity-large-thinking"
}
},
"compat": {
"supportsStore": true,
"supportsDeveloperRole": false,
"supportsMultipleSystemMessages": false,
"supportsReasoningEffort": true,
"supportsReasoningParams": true,
"reasoningEffortMap": {},
"supportsUsageInStreaming": true,
"alwaysSendMaxTokens": false,
"disableReasoningOnForcedToolChoice": false,
"disableReasoningOnToolChoice": false,
"supportsToolChoice": true,
"maxTokensField": "max_completion_tokens",
"requiresToolResultName": false,
"requiresAssistantAfterToolResult": false,
"requiresThinkingAsText": false,
"requiresMistralToolIds": false,
"thinkingFormat": "openai",
"reasoningContentField": "reasoning_content",
"requiresReasoningContentForToolCalls": false,
"allowsSyntheticReasoningContentForToolCalls": true,
"requiresAssistantContentForToolCalls": false,
"isOpenRouterHost": false,
"isVercelGatewayHost": false,
"supportsStrictMode": false,
"toolStrictMode": "mixed"
}
},
"arcee-ai/trinity-large-preview": {
"id": "arcee-ai/trinity-large-preview",
"name": "Trinity Large Preview",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.25,
"output": 1,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131000,
"maxTokens": 131000
},
"arcee-ai/trinity-mini": {
"id": "arcee-ai/trinity-mini",
"name": "Trinity Mini",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.045,
"output": 0.15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"asi1-mini": {
"id": "asi1-mini",
"name": "asi1-mini",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"auto-model": {
"id": "auto-model",
"name": "auto-model",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"auto-model-basic": {
"id": "auto-model-basic",
"name": "auto-model-basic",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"auto-model-premium": {
"id": "auto-model-premium",
"name": "auto-model-premium",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"auto-model-standard": {
"id": "auto-model-standard",
"name": "auto-model-standard",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"azure-gpt-4-turbo": {
"id": "azure-gpt-4-turbo",
"name": "azure-gpt-4-turbo",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"azure-gpt-4o": {
"id": "azure-gpt-4o",
"name": "Azure gpt-4o",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2.499,
"output": 9.996,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"azure-gpt-4o-mini": {
"id": "azure-gpt-4o-mini",
"name": "Azure gpt-4o-mini",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1496,
"output": 0.595,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"azure-o1": {
"id": "azure-o1",
"name": "azure-o1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"azure-o3-mini": {
"id": "azure-o3-mini",
"name": "azure-o3-mini",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000
},
"Baichuan-M2": {
"id": "Baichuan-M2",
"name": "Baichuan-M2",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Baichuan4-Air": {
"id": "Baichuan4-Air",
"name": "Baichuan4-Air",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Baichuan4-Turbo": {
"id": "Baichuan4-Turbo",
"name": "Baichuan4-Turbo",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"baidu/ernie-4.5-300b-a47b": {
"id": "baidu/ernie-4.5-300b-a47b",
"name": "baidu/ernie-4.5-300b-a47b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"baidu/ernie-4.5-vl-28b-a3b": {
"id": "baidu/ernie-4.5-vl-28b-a3b",
"name": "ERNIE 4.5 VL 28B A3B",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.14,
"output": 0.56,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"baseten/Kimi-K2-Instruct-FP4": {
"id": "baseten/Kimi-K2-Instruct-FP4",
"name": "baseten/Kimi-K2-Instruct-FP4",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384
},
"brave": {
"id": "brave",
"name": "brave",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"brave-pro": {
"id": "brave-pro",
"name": "brave-pro",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"brave-research": {
"id": "brave-research",
"name": "brave-research",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"bytedance-seed/seed-2.0-lite": {
"id": "bytedance-seed/seed-2.0-lite",
"name": "Seed-2.0-Lite",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"chutesai/Mistral-Small-3.2-24B-Instruct-2506": {
"id": "chutesai/Mistral-Small-3.2-24B-Instruct-2506",
"name": "chutesai/Mistral-Small-3.2-24B-Instruct-2506",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"claude-3-5-haiku-20241022": {
"id": "claude-3-5-haiku-20241022",
"name": "Claude 3.5 Haiku",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.8,
"output": 4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 8192
},
"claude-3-5-sonnet-20240620": {
"id": "claude-3-5-sonnet-20240620",
"name": "Claude Sonnet 3.5",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 8192
},
"claude-3-5-sonnet-20241022": {
"id": "claude-3-5-sonnet-20241022",
"name": "Claude Sonnet 3.5 v2",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 8192
},
"claude-3-7-sonnet-20250219": {
"id": "claude-3-7-sonnet-20250219",
"name": "claude-3-7-sonnet-20250219",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 4096,
"maxTokens": 4096
},
"claude-3-7-sonnet-reasoner": {
"id": "claude-3-7-sonnet-reasoner",
"name": "claude-3-7-sonnet-reasoner",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"claude-3-7-sonnet-thinking": {
"id": "claude-3-7-sonnet-thinking",
"name": "claude-3-7-sonnet-thinking",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"claude-3-7-sonnet-thinking:1024": {
"id": "claude-3-7-sonnet-thinking:1024",
"name": "claude-3-7-sonnet-thinking:1024",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"claude-3-7-sonnet-thinking:128000": {
"id": "claude-3-7-sonnet-thinking:128000",
"name": "claude-3-7-sonnet-thinking:128000",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"claude-3-7-sonnet-thinking:32768": {
"id": "claude-3-7-sonnet-thinking:32768",
"name": "claude-3-7-sonnet-thinking:32768",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"claude-3-7-sonnet-thinking:8192": {
"id": "claude-3-7-sonnet-thinking:8192",
"name": "claude-3-7-sonnet-thinking:8192",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"claude-haiku-4-5-20251001": {
"id": "claude-haiku-4-5-20251001",
"name": "Claude Haiku 4.5",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 1,
"output": 5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000
},
"claude-haiku-4-5-20251001-thinking": {
"id": "claude-haiku-4-5-20251001-thinking",
"name": "Claude Haiku 4.5 Thinking",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1,
"output": 5,
"cacheRead": 0.1,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"claude-opus-4-1-20250805": {
"id": "claude-opus-4-1-20250805",
"name": "Claude 4.1 Opus",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 14.994,
"output": 75.004,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 32000
},
"claude-opus-4-1-thinking": {
"id": "claude-opus-4-1-thinking",
"name": "Claude 4.1 Opus Thinking",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 14.994,
"output": 75.004,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"claude-opus-4-1-thinking:1024": {
"id": "claude-opus-4-1-thinking:1024",
"name": "Claude 4.1 Opus Thinking (1K)",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 14.994,
"output": 75.004,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"claude-opus-4-1-thinking:32000": {
"id": "claude-opus-4-1-thinking:32000",
"name": "Claude 4.1 Opus Thinking (32K)",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 14.994,
"output": 75.004,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"claude-opus-4-1-thinking:32768": {
"id": "claude-opus-4-1-thinking:32768",
"name": "Claude 4.1 Opus Thinking (32K)",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 14.994,
"output": 75.004,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"claude-opus-4-1-thinking:8192": {
"id": "claude-opus-4-1-thinking:8192",
"name": "Claude 4.1 Opus Thinking (8K)",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 14.994,
"output": 75.004,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"claude-opus-4-20250514": {
"id": "claude-opus-4-20250514",
"name": "Claude 4 Opus",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 14.994,
"output": 75.004,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 32000
},
"claude-opus-4-5-20251101": {
"id": "claude-opus-4-5-20251101",
"name": "Claude 4.5 Opus",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 4.998,
"output": 25.007,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-opus-4-5-20251101:thinking": {
"id": "claude-opus-4-5-20251101:thinking",
"name": "Claude 4.5 Opus Thinking",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 4.998,
"output": 25.007,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-opus-4-thinking": {
"id": "claude-opus-4-thinking",
"name": "Claude 4 Opus Thinking",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 14.994,
"output": 75.004,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"claude-opus-4-thinking:1024": {
"id": "claude-opus-4-thinking:1024",
"name": "Claude 4 Opus Thinking (1K)",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 14.994,
"output": 75.004,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"claude-opus-4-thinking:32000": {
"id": "claude-opus-4-thinking:32000",
"name": "Claude 4 Opus Thinking (32K)",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 14.994,
"output": 75.004,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"claude-opus-4-thinking:32768": {
"id": "claude-opus-4-thinking:32768",
"name": "Claude 4 Opus Thinking (32K)",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 14.994,
"output": 75.004,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"claude-opus-4-thinking:8192": {
"id": "claude-opus-4-thinking:8192",
"name": "Claude 4 Opus Thinking (8K)",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 14.994,
"output": 75.004,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"claude-sonnet-4-20250514": {
"id": "claude-sonnet-4-20250514",
"name": "Claude 4 Sonnet",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2.992,
"output": 14.994,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000
},
"claude-sonnet-4-5-20250929": {
"id": "claude-sonnet-4-5-20250929",
"name": "Claude Sonnet 4.5",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.992,
"output": 14.994,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortRouting": {
"off": "claude-sonnet-4-5-20250929",
"minimal": "claude-sonnet-4-5-20250929-thinking",
"low": "claude-sonnet-4-5-20250929-thinking",
"medium": "claude-sonnet-4-5-20250929-thinking",
"high": "claude-sonnet-4-5-20250929-thinking",
"xhigh": "claude-sonnet-4-5-20250929-thinking"
}
}
},
"claude-sonnet-4-thinking": {
"id": "claude-sonnet-4-thinking",
"name": "Claude 4 Sonnet Thinking",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.992,
"output": 14.994,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"claude-sonnet-4-thinking:1024": {
"id": "claude-sonnet-4-thinking:1024",
"name": "Claude 4 Sonnet Thinking (1K)",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.992,
"output": 14.994,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"claude-sonnet-4-thinking:32768": {
"id": "claude-sonnet-4-thinking:32768",
"name": "Claude 4 Sonnet Thinking (32K)",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.992,
"output": 14.994,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"claude-sonnet-4-thinking:64000": {
"id": "claude-sonnet-4-thinking:64000",
"name": "Claude 4 Sonnet Thinking (64K)",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.992,
"output": 14.994,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"claude-sonnet-4-thinking:8192": {
"id": "claude-sonnet-4-thinking:8192",
"name": "Claude 4 Sonnet Thinking (8K)",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.992,
"output": 14.994,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"claw-high": {
"id": "claw-high",
"name": "Claw High",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 4.998,
"output": 25.007,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claw-low": {
"id": "claw-low",
"name": "Claw Low",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 1.5,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claw-medium": {
"id": "claw-medium",
"name": "Claw Medium",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"cognitivecomputations/dolphin-2.9.2-qwen2-72b": {
"id": "cognitivecomputations/dolphin-2.9.2-qwen2-72b",
"name": "cognitivecomputations/dolphin-2.9.2-qwen2-72b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"cohere/command-r": {
"id": "cohere/command-r",
"name": "cohere/command-r",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"cohere/command-r-plus-08-2024": {
"id": "cohere/command-r-plus-08-2024",
"name": "Command R+",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 2.856,
"output": 14.246,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"command-a-plus-05-2026": {
"id": "command-a-plus-05-2026",
"name": "command-a-plus-05-2026",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"command-a-reasoning-08-2025": {
"id": "command-a-reasoning-08-2025",
"name": "command-a-reasoning-08-2025",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"CrucibleLab/L3.3-70B-Loki-V2.0": {
"id": "CrucibleLab/L3.3-70B-Loki-V2.0",
"name": "CrucibleLab/L3.3-70B-Loki-V2.0",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"deepclaude": {
"id": "deepclaude",
"name": "deepclaude",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"deepcogito/cogito-v1-preview-qwen-32B": {
"id": "deepcogito/cogito-v1-preview-qwen-32B",
"name": "deepcogito/cogito-v1-preview-qwen-32B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"deepcogito/cogito-v2.1-671b": {
"id": "deepcogito/cogito-v2.1-671b",
"name": "deepcogito/cogito-v2.1-671b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"deepseek-ai/DeepSeek-R1-0528": {
"id": "deepseek-ai/DeepSeek-R1-0528",
"name": "DeepSeek-R1-0528",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek-ai/DeepSeek-V3.1": {
"id": "deepseek-ai/DeepSeek-V3.1",
"name": "DeepSeek V3.1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 1.25,
"cacheRead": 0.6,
"cacheWrite": 0.6
},
"contextWindow": 131072,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek-ai/DeepSeek-V3.1-Terminus": {
"id": "deepseek-ai/DeepSeek-V3.1-Terminus",
"name": "DeepSeek V3.1 Terminus",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.25,
"output": 0.7,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 65536
},
"deepseek-ai/DeepSeek-V3.1-Terminus:thinking": {
"id": "deepseek-ai/DeepSeek-V3.1-Terminus:thinking",
"name": "DeepSeek V3.1 Terminus (Thinking)",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.25,
"output": 0.7,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 65536
},
"deepseek-ai/deepseek-v3.2-exp": {
"id": "deepseek-ai/deepseek-v3.2-exp",
"name": "deepseek-ai/deepseek-v3.2-exp",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
},
"effortRouting": {
"off": "deepseek-ai/deepseek-v3.2-exp",
"minimal": "deepseek-ai/deepseek-v3.2-exp-thinking",
"low": "deepseek-ai/deepseek-v3.2-exp-thinking",
"medium": "deepseek-ai/deepseek-v3.2-exp-thinking",
"high": "deepseek-ai/deepseek-v3.2-exp-thinking",
"xhigh": "deepseek-ai/deepseek-v3.2-exp-thinking"
}
},
"compat": {
"supportsStore": true,
"supportsDeveloperRole": false,
"supportsMultipleSystemMessages": true,
"supportsReasoningEffort": true,
"supportsReasoningParams": true,
"reasoningEffortMap": {},
"supportsUsageInStreaming": true,
"alwaysSendMaxTokens": false,
"disableReasoningOnForcedToolChoice": false,
"disableReasoningOnToolChoice": false,
"supportsToolChoice": true,
"maxTokensField": "max_completion_tokens",
"requiresToolResultName": false,
"requiresAssistantAfterToolResult": false,
"requiresThinkingAsText": false,
"requiresMistralToolIds": false,
"thinkingFormat": "openai",
"reasoningContentField": "reasoning_content",
"requiresReasoningContentForToolCalls": false,
"allowsSyntheticReasoningContentForToolCalls": true,
"requiresAssistantContentForToolCalls": false,
"isOpenRouterHost": false,
"isVercelGatewayHost": false,
"supportsStrictMode": false,
"toolStrictMode": "mixed"
}
},
"deepseek-chat": {
"id": "deepseek-chat",
"name": "DeepSeek V3/Deepseek Chat",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.25,
"output": 0.7,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"deepseek-chat-cheaper": {
"id": "deepseek-chat-cheaper",
"name": "DeepSeek V3/Chat Cheaper",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.25,
"output": 0.7,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"deepseek-math-v2": {
"id": "deepseek-math-v2",
"name": "deepseek-math-v2",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"deepseek-r1": {
"id": "deepseek-r1",
"name": "deepseek-r1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 16000
},
"deepseek-r1-sambanova": {
"id": "deepseek-r1-sambanova",
"name": "deepseek-r1-sambanova",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"deepseek-reasoner": {
"id": "deepseek-reasoner",
"name": "deepseek-reasoner",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"deepseek-reasoner-cheaper": {
"id": "deepseek-reasoner-cheaper",
"name": "deepseek-reasoner-cheaper",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"deepseek-v3-0324": {
"id": "deepseek-v3-0324",
"name": "DeepSeek Chat 0324",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.25,
"output": 0.7,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"deepseek/deepseek-latest": {
"id": "deepseek/deepseek-latest",
"name": "DeepSeek Latest",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.1,
"output": 2.2,
"cacheRead": 0.11,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 384000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek/deepseek-prover-v2-671b": {
"id": "deepseek/deepseek-prover-v2-671b",
"name": "deepseek/deepseek-prover-v2-671b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"deepseek/deepseek-v3.2": {
"id": "deepseek/deepseek-v3.2",
"name": "DeepSeek V3.2",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.27999999999999997,
"output": 0.42000000000000004,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 163000,
"maxTokens": 65536
},
"deepseek/deepseek-v3.2-speciale": {
"id": "deepseek/deepseek-v3.2-speciale",
"name": "deepseek/deepseek-v3.2-speciale",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"deepseek/deepseek-v3.2:thinking": {
"id": "deepseek/deepseek-v3.2:thinking",
"name": "DeepSeek V3.2 Thinking",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.27999999999999997,
"output": 0.42000000000000004,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 163000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek/deepseek-v4-flash": {
"id": "deepseek/deepseek-v4-flash",
"name": "DeepSeek V4 Flash",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.14,
"output": 0.28,
"cacheRead": 0.028,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 384000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek/deepseek-v4-flash:thinking": {
"id": "deepseek/deepseek-v4-flash:thinking",
"name": "DeepSeek V4 Flash (Thinking)",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.14,
"output": 0.28,
"cacheRead": 0.028,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 384000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek/deepseek-v4-pro": {
"id": "deepseek/deepseek-v4-pro",
"name": "DeepSeek V4 Pro",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.1,
"output": 2.2,
"cacheRead": 0.11,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 384000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek/deepseek-v4-pro-cheaper": {
"id": "deepseek/deepseek-v4-pro-cheaper",
"name": "DeepSeek V4 Pro Cheaper",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.435,
"output": 0.87,
"cacheRead": 0.003625,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 384000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek/deepseek-v4-pro-cheaper:thinking": {
"id": "deepseek/deepseek-v4-pro-cheaper:thinking",
"name": "DeepSeek V4 Pro Cheaper (Thinking)",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.435,
"output": 0.87,
"cacheRead": 0.003625,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 384000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek/deepseek-v4-pro:thinking": {
"id": "deepseek/deepseek-v4-pro:thinking",
"name": "DeepSeek V4 Pro (Thinking)",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.1,
"output": 2.2,
"cacheRead": 0.11,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 384000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"dmind/dmind-1": {
"id": "dmind/dmind-1",
"name": "dmind/dmind-1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"dmind/dmind-1-mini": {
"id": "dmind/dmind-1-mini",
"name": "dmind/dmind-1-mini",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Doctor-Shotgun/MS3.2-24B-Magnum-Diamond": {
"id": "Doctor-Shotgun/MS3.2-24B-Magnum-Diamond",
"name": "Doctor-Shotgun/MS3.2-24B-Magnum-Diamond",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"doubao-1-5-thinking-pro-250415": {
"id": "doubao-1-5-thinking-pro-250415",
"name": "doubao-1-5-thinking-pro-250415",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"doubao-1.5-pro-256k": {
"id": "doubao-1.5-pro-256k",
"name": "doubao-1.5-pro-256k",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"doubao-1.5-pro-32k": {
"id": "doubao-1.5-pro-32k",
"name": "doubao-1.5-pro-32k",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"doubao-seed-1-6-250615": {
"id": "doubao-seed-1-6-250615",
"name": "doubao-seed-1-6-250615",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortRouting": {
"off": "doubao-seed-1-6-250615",
"minimal": "doubao-seed-1-6-thinking-250615",
"low": "doubao-seed-1-6-thinking-250615",
"medium": "doubao-seed-1-6-thinking-250615",
"high": "doubao-seed-1-6-thinking-250615",
"xhigh": "doubao-seed-1-6-thinking-250615"
}
},
"compat": {
"supportsStore": true,
"supportsDeveloperRole": false,
"supportsMultipleSystemMessages": false,
"supportsReasoningEffort": true,
"supportsReasoningParams": true,
"reasoningEffortMap": {},
"supportsUsageInStreaming": true,
"alwaysSendMaxTokens": false,
"disableReasoningOnForcedToolChoice": false,
"disableReasoningOnToolChoice": false,
"supportsToolChoice": true,
"maxTokensField": "max_completion_tokens",
"requiresToolResultName": false,
"requiresAssistantAfterToolResult": false,
"requiresThinkingAsText": false,
"requiresMistralToolIds": false,
"thinkingFormat": "openai",
"reasoningContentField": "reasoning_content",
"requiresReasoningContentForToolCalls": false,
"allowsSyntheticReasoningContentForToolCalls": true,
"requiresAssistantContentForToolCalls": false,
"isOpenRouterHost": false,
"isVercelGatewayHost": false,
"supportsStrictMode": false,
"toolStrictMode": "mixed"
}
},
"doubao-seed-1-6-flash-250615": {
"id": "doubao-seed-1-6-flash-250615",
"name": "doubao-seed-1-6-flash-250615",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"doubao-seed-1-8-251215": {
"id": "doubao-seed-1-8-251215",
"name": "doubao-seed-1-8-251215",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"doubao-seed-2-0-code-preview-260215": {
"id": "doubao-seed-2-0-code-preview-260215",
"name": "doubao-seed-2-0-code-preview-260215",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"doubao-seed-2-0-lite-260215": {
"id": "doubao-seed-2-0-lite-260215",
"name": "doubao-seed-2-0-lite-260215",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"doubao-seed-2-0-mini-260215": {
"id": "doubao-seed-2-0-mini-260215",
"name": "doubao-seed-2-0-mini-260215",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"doubao-seed-2-0-pro-260215": {
"id": "doubao-seed-2-0-pro-260215",
"name": "doubao-seed-2-0-pro-260215",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"doubao-seed-code-preview-latest": {
"id": "doubao-seed-code-preview-latest",
"name": "doubao-seed-code-preview-latest",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Envoid/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B": {
"id": "Envoid/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B",
"name": "Envoid/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Envoid/Llama-3.05-NT-Storybreaker-Ministral-70B": {
"id": "Envoid/Llama-3.05-NT-Storybreaker-Ministral-70B",
"name": "Envoid/Llama-3.05-NT-Storybreaker-Ministral-70B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"ernie-4.5-8k-preview": {
"id": "ernie-4.5-8k-preview",
"name": "ernie-4.5-8k-preview",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"ernie-4.5-turbo-128k": {
"id": "ernie-4.5-turbo-128k",
"name": "ernie-4.5-turbo-128k",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"ernie-4.5-turbo-vl-32k": {
"id": "ernie-4.5-turbo-vl-32k",
"name": "ernie-4.5-turbo-vl-32k",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"ernie-5.0-thinking-latest": {
"id": "ernie-5.0-thinking-latest",
"name": "ernie-5.0-thinking-latest",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"ernie-5.0-thinking-preview": {
"id": "ernie-5.0-thinking-preview",
"name": "ernie-5.0-thinking-preview",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 64000
},
"ernie-5.1": {
"id": "ernie-5.1",
"name": "ernie-5.1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": null,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"ernie-x1-32k": {
"id": "ernie-x1-32k",
"name": "ernie-x1-32k",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"ernie-x1-32k-preview": {
"id": "ernie-x1-32k-preview",
"name": "ernie-x1-32k-preview",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"ernie-x1-turbo-32k": {
"id": "ernie-x1-turbo-32k",
"name": "ernie-x1-turbo-32k",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"ernie-x1.1-preview": {
"id": "ernie-x1.1-preview",
"name": "ernie-x1.1-preview",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 65536,
"maxTokens": null
},
"essentialai/rnj-1-instruct": {
"id": "essentialai/rnj-1-instruct",
"name": "Rnj 1 Instruct",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32768,
"maxTokens": 32768
},
"EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0": {
"id": "EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0",
"name": "EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1": {
"id": "EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1",
"name": "EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2": {
"id": "EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2",
"name": "EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2": {
"id": "EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2",
"name": "EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"exa-answer": {
"id": "exa-answer",
"name": "exa-answer",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"exa-research": {
"id": "exa-research",
"name": "exa-research",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"exa-research-pro": {
"id": "exa-research-pro",
"name": "exa-research-pro",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5": {
"id": "failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5",
"name": "failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"fastgpt": {
"id": "fastgpt",
"name": "fastgpt",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"featherless-ai/Qwerky-72B": {
"id": "featherless-ai/Qwerky-72B",
"name": "featherless-ai/Qwerky-72B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"GalrionSoftworks/MN-LooseCannon-12B-v1": {
"id": "GalrionSoftworks/MN-LooseCannon-12B-v1",
"name": "GalrionSoftworks/MN-LooseCannon-12B-v1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gemini-2.0-flash-001": {
"id": "gemini-2.0-flash-001",
"name": "Gemini 2.0 Flash",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1003,
"output": 0.408,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 8192
},
"gemini-2.0-flash-lite": {
"id": "gemini-2.0-flash-lite",
"name": "Gemini 2.0 Flash-Lite",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.075,
"output": 0.3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 8192
},
"gemini-2.0-flash-thinking-exp-01-21": {
"id": "gemini-2.0-flash-thinking-exp-01-21",
"name": "gemini-2.0-flash-thinking-exp-01-21",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gemini-2.0-flash-thinking-exp-1219": {
"id": "gemini-2.0-flash-thinking-exp-1219",
"name": "gemini-2.0-flash-thinking-exp-1219",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gemini-2.0-pro-exp-02-05": {
"id": "gemini-2.0-pro-exp-02-05",
"name": "gemini-2.0-pro-exp-02-05",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gemini-2.0-pro-reasoner": {
"id": "gemini-2.0-pro-reasoner",
"name": "gemini-2.0-pro-reasoner",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gemini-2.5-flash": {
"id": "gemini-2.5-flash",
"name": "Gemini 2.5 Flash",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 2.5,
"cacheRead": 0.075,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gemini-2.5-flash-lite": {
"id": "gemini-2.5-flash-lite",
"name": "Gemini 2.5 Flash-Lite",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1,
"output": 0.4,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gemini-2.5-flash-lite-preview-06-17": {
"id": "gemini-2.5-flash-lite-preview-06-17",
"name": "Gemini 2.5 Flash Lite Preview 06-17",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1,
"output": 0.4,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gemini-2.5-flash-lite-preview-09-2025": {
"id": "gemini-2.5-flash-lite-preview-09-2025",
"name": "Gemini 2.5 Flash Lite Preview (09/2025)",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1,
"output": 0.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048756,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortRouting": {
"off": "gemini-2.5-flash-lite-preview-09-2025",
"minimal": "gemini-2.5-flash-lite-preview-09-2025-thinking",
"low": "gemini-2.5-flash-lite-preview-09-2025-thinking",
"medium": "gemini-2.5-flash-lite-preview-09-2025-thinking",
"high": "gemini-2.5-flash-lite-preview-09-2025-thinking"
}
}
},
"gemini-2.5-flash-nothinking": {
"id": "gemini-2.5-flash-nothinking",
"name": "gemini-2.5-flash-nothinking",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gemini-2.5-flash-preview-04-17": {
"id": "gemini-2.5-flash-preview-04-17",
"name": "Gemini 2.5 Flash Preview 04-17",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0.0375,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gemini-2.5-flash-preview-05-20": {
"id": "gemini-2.5-flash-preview-05-20",
"name": "Gemini 2.5 Flash Preview 05-20",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0.0375,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gemini-2.5-flash-preview-09-2025": {
"id": "gemini-2.5-flash-preview-09-2025",
"name": "Gemini 2.5 Flash Preview (09/2025)",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 2.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048756,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortRouting": {
"off": "gemini-2.5-flash-preview-09-2025",
"minimal": "gemini-2.5-flash-preview-09-2025-thinking",
"low": "gemini-2.5-flash-preview-09-2025-thinking",
"medium": "gemini-2.5-flash-preview-09-2025-thinking",
"high": "gemini-2.5-flash-preview-09-2025-thinking"
}
}
},
"gemini-2.5-pro": {
"id": "gemini-2.5-pro",
"name": "Gemini 2.5 Pro",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.31,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"headers": {
"User-Agent": "opencode/1.3.15"
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
},
"compat": {
"supportsStore": false,
"supportsDeveloperRole": false,
"supportsReasoningEffort": false
}
},
"gemini-2.5-pro-exp-03-25": {
"id": "gemini-2.5-pro-exp-03-25",
"name": "gemini-2.5-pro-exp-03-25",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gemini-2.5-pro-preview-03-25": {
"id": "gemini-2.5-pro-preview-03-25",
"name": "gemini-2.5-pro-preview-03-25",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gemini-2.5-pro-preview-05-06": {
"id": "gemini-2.5-pro-preview-05-06",
"name": "Gemini 2.5 Pro Preview 05-06",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.31,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"gemini-2.5-pro-preview-06-05": {
"id": "gemini-2.5-pro-preview-06-05",
"name": "Gemini 2.5 Pro Preview 06-05",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.31,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"gemini-3-pro-preview": {
"id": "gemini-3-pro-preview",
"name": "Gemini 3 Pro Preview",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"high"
],
"effortRouting": {
"off": "gemini-3-pro-preview",
"low": "gemini-3-pro-preview-thinking",
"high": "gemini-3-pro-preview-thinking"
},
"requiresEffort": true
},
"compat": {
"supportsStore": true,
"supportsDeveloperRole": false,
"supportsMultipleSystemMessages": false,
"supportsReasoningEffort": true,
"supportsReasoningParams": true,
"reasoningEffortMap": {},
"supportsUsageInStreaming": false,
"alwaysSendMaxTokens": false,
"disableReasoningOnForcedToolChoice": false,
"disableReasoningOnToolChoice": false,
"supportsToolChoice": true,
"maxTokensField": "max_completion_tokens",
"requiresToolResultName": false,
"requiresAssistantAfterToolResult": false,
"requiresThinkingAsText": false,
"requiresMistralToolIds": false,
"thinkingFormat": "openai",
"reasoningContentField": "reasoning_content",
"requiresReasoningContentForToolCalls": false,
"allowsSyntheticReasoningContentForToolCalls": true,
"requiresAssistantContentForToolCalls": false,
"isOpenRouterHost": false,
"isVercelGatewayHost": false,
"supportsStrictMode": false,
"toolStrictMode": "mixed"
}
},
"gemini-exp-1206": {
"id": "gemini-exp-1206",
"name": "gemini-exp-1206",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Gemma-3-27B-ArliAI-RPMax-v3": {
"id": "Gemma-3-27B-ArliAI-RPMax-v3",
"name": "Gemma-3-27B-ArliAI-RPMax-v3",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Gemma-3-27B-Big-Tiger-v3": {
"id": "Gemma-3-27B-Big-Tiger-v3",
"name": "Gemma-3-27B-Big-Tiger-v3",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Gemma-3-27B-CardProjector-v4": {
"id": "Gemma-3-27B-CardProjector-v4",
"name": "Gemma-3-27B-CardProjector-v4",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Gemma-3-27B-Glitter": {
"id": "Gemma-3-27B-Glitter",
"name": "Gemma-3-27B-Glitter",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Gemma-3-27B-it": {
"id": "Gemma-3-27B-it",
"name": "Gemma-3-27B-it",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192
},
"Gemma-3-27B-it-Abliterated": {
"id": "Gemma-3-27B-it-Abliterated",
"name": "Gemma-3-27B-it-Abliterated",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Gemma-3-27B-Nidum-Uncensored": {
"id": "Gemma-3-27B-Nidum-Uncensored",
"name": "Gemma-3-27B-Nidum-Uncensored",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled": {
"id": "Gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled",
"name": "Gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Gemma-4-31B-Cognitive-Unshackled": {
"id": "Gemma-4-31B-Cognitive-Unshackled",
"name": "Gemma-4-31B-Cognitive-Unshackled",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Gemma-4-31B-DarkIdol": {
"id": "Gemma-4-31B-DarkIdol",
"name": "Gemma-4-31B-DarkIdol",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gemma-4-31B-Fabled": {
"id": "gemma-4-31B-Fabled",
"name": "gemma-4-31B-Fabled",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gemma-4-31B-Garnet": {
"id": "gemma-4-31B-Garnet",
"name": "gemma-4-31B-Garnet",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Gemma-4-31B-GarnetV2": {
"id": "Gemma-4-31B-GarnetV2",
"name": "Gemma-4-31B-GarnetV2",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Gemma-4-31B-Gemopus": {
"id": "Gemma-4-31B-Gemopus",
"name": "Gemma-4-31B-Gemopus",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Gemma-4-31B-it": {
"id": "Gemma-4-31B-it",
"name": "Gemma-4-31B-it",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768
},
"gemma-4-31B-K1-v5": {
"id": "gemma-4-31B-K1-v5",
"name": "gemma-4-31B-K1-v5",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gemma-4-31B-Larkspur-v0.5": {
"id": "gemma-4-31B-Larkspur-v0.5",
"name": "gemma-4-31B-Larkspur-v0.5",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"gemma-4-31B-MeroMero": {
"id": "gemma-4-31B-MeroMero",
"name": "gemma-4-31B-MeroMero",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Gemma-4-31B-Musica-v1": {
"id": "Gemma-4-31B-Musica-v1",
"name": "Gemma-4-31B-Musica-v1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Gemma-4-31B-Queen": {
"id": "Gemma-4-31B-Queen",
"name": "Gemma-4-31B-Queen",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"glm-4": {
"id": "glm-4",
"name": "glm-4",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"glm-4-air": {
"id": "glm-4-air",
"name": "glm-4-air",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"glm-4-air-0111": {
"id": "glm-4-air-0111",
"name": "glm-4-air-0111",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"glm-4-airx": {
"id": "glm-4-airx",
"name": "glm-4-airx",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"glm-4-flash": {
"id": "glm-4-flash",
"name": "glm-4-flash",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"glm-4-long": {
"id": "glm-4-long",
"name": "glm-4-long",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"glm-4-plus": {
"id": "glm-4-plus",
"name": "glm-4-plus",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"glm-4-plus-0111": {
"id": "glm-4-plus-0111",
"name": "glm-4-plus-0111",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"glm-4.1v-thinking-flash": {
"id": "glm-4.1v-thinking-flash",
"name": "glm-4.1v-thinking-flash",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"glm-4.1v-thinking-flashx": {
"id": "glm-4.1v-thinking-flashx",
"name": "glm-4.1v-thinking-flashx",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"GLM-4.5-Air-Derestricted": {
"id": "GLM-4.5-Air-Derestricted",
"name": "GLM-4.5-Air-Derestricted",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"GLM-4.5-Air-Derestricted-Iceblink": {
"id": "GLM-4.5-Air-Derestricted-Iceblink",
"name": "GLM-4.5-Air-Derestricted-Iceblink",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"GLM-4.5-Air-Derestricted-Iceblink-ReExtract": {
"id": "GLM-4.5-Air-Derestricted-Iceblink-ReExtract",
"name": "GLM-4.5-Air-Derestricted-Iceblink-ReExtract",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"GLM-4.5-Air-Derestricted-Iceblink-v2": {
"id": "GLM-4.5-Air-Derestricted-Iceblink-v2",
"name": "GLM-4.5-Air-Derestricted-Iceblink-v2",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"GLM-4.5-Air-Derestricted-Iceblink-v2-ReExtract": {
"id": "GLM-4.5-Air-Derestricted-Iceblink-v2-ReExtract",
"name": "GLM-4.5-Air-Derestricted-Iceblink-v2-ReExtract",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"GLM-4.5-Air-Derestricted-Steam": {
"id": "GLM-4.5-Air-Derestricted-Steam",
"name": "GLM-4.5-Air-Derestricted-Steam",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"GLM-4.5-Air-Derestricted-Steam-ReExtract": {
"id": "GLM-4.5-Air-Derestricted-Steam-ReExtract",
"name": "GLM-4.5-Air-Derestricted-Steam-ReExtract",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"GLM-4.6-Derestricted-v5": {
"id": "GLM-4.6-Derestricted-v5",
"name": "GLM-4.6-Derestricted-v5",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"glm-4.7-flash-heretic": {
"id": "glm-4.7-flash-heretic",
"name": "glm-4.7-flash-heretic",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"glm-z1-air": {
"id": "glm-z1-air",
"name": "GLM Z1 Air",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.07,
"output": 0.07,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32000,
"maxTokens": 16384
},
"glm-z1-airx": {
"id": "glm-z1-airx",
"name": "GLM Z1 AirX",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.7,
"output": 0.7,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32000,
"maxTokens": 16384
},
"glm-zero-preview": {
"id": "glm-zero-preview",
"name": "glm-zero-preview",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"google/gemini-3-flash-preview": {
"id": "google/gemini-3-flash-preview",
"name": "Gemini 3 Flash (Preview)",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.5,
"output": 3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048756,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3.1-flash-lite": {
"id": "google/gemini-3.1-flash-lite",
"name": "Gemini 3.1 Flash Lite",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 1.5,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3.1-flash-lite-preview": {
"id": "google/gemini-3.1-flash-lite-preview",
"name": "Gemini 3.1 Flash Lite Preview",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 1.5,
"cacheRead": 0.024999999999999998,
"cacheWrite": 0.08333333333333334
},
"contextWindow": 1050000,
"maxTokens": 65530
},
"google/gemini-3.1-pro-preview": {
"id": "google/gemini-3.1-pro-preview",
"name": "Gemini 3.1 Pro (Preview)",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 12,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 1048756,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3.1-pro-preview-customtools": {
"id": "google/gemini-3.1-pro-preview-customtools",
"name": "Gemini 3.1 Pro (Preview Custom Tools)",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 12,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 1048756,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3.1-pro-preview-high": {
"id": "google/gemini-3.1-pro-preview-high",
"name": "Gemini 3.1 Pro (Preview High)",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 12,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 1048756,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3.1-pro-preview-low": {
"id": "google/gemini-3.1-pro-preview-low",
"name": "Gemini 3.1 Pro (Preview Low)",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 12,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 1048756,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3.5-flash": {
"id": "google/gemini-3.5-flash",
"name": "Gemini 3.5 Flash",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.5,
"output": 9,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"google/gemini-flash-1.5": {
"id": "google/gemini-flash-1.5",
"name": "google/gemini-flash-1.5",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"google/gemini-flash-latest": {
"id": "google/gemini-flash-latest",
"name": "google/gemini-flash-latest",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536
},
"google/gemini-flash-lite-latest": {
"id": "google/gemini-flash-lite-latest",
"name": "Gemini Flash Lite Latest",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 1.5,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"google/gemini-pro-latest": {
"id": "google/gemini-pro-latest",
"name": "Gemini Pro Latest",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 12,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 1048756,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"google/gemma-4-26b-a4b-it": {
"id": "google/gemma-4-26b-a4b-it",
"name": "Gemma 4 26B A4B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.13,
"output": 0.39999999999999997,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"google/gemma-4-31b-it": {
"id": "google/gemma-4-31b-it",
"name": "Gemma 4 31B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"grok-3-beta": {
"id": "grok-3-beta",
"name": "grok-3-beta",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": null
},
"grok-3-fast-beta": {
"id": "grok-3-fast-beta",
"name": "grok-3-fast-beta",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"grok-3-mini-beta": {
"id": "grok-3-mini-beta",
"name": "grok-3-mini-beta",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": null
},
"grok-3-mini-fast-beta": {
"id": "grok-3-mini-fast-beta",
"name": "grok-3-mini-fast-beta",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Gryphe/MythoMax-L2-13b": {
"id": "Gryphe/MythoMax-L2-13b",
"name": "Gryphe/MythoMax-L2-13b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"hermes-high": {
"id": "hermes-high",
"name": "Hermes High",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 4.998,
"output": 25.007,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"hermes-low": {
"id": "hermes-low",
"name": "Hermes Low",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 1.5,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"hermes-medium": {
"id": "hermes-medium",
"name": "Hermes Medium",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"holo3-35b-a3b": {
"id": "holo3-35b-a3b",
"name": "Holo3-35B-A3B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 1.8,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 65536,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"holo3-35b-a3b:thinking": {
"id": "holo3-35b-a3b:thinking",
"name": "Holo3-35B-A3B Thinking",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 1.8,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 65536,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated": {
"id": "huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated",
"name": "huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated": {
"id": "huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated",
"name": "huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"huihui-ai/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated": {
"id": "huihui-ai/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated",
"name": "huihui-ai/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"huihui-ai/Llama-3.3-70B-Instruct-abliterated": {
"id": "huihui-ai/Llama-3.3-70B-Instruct-abliterated",
"name": "huihui-ai/Llama-3.3-70B-Instruct-abliterated",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"huihui-ai/Qwen2.5-32B-Instruct-abliterated": {
"id": "huihui-ai/Qwen2.5-32B-Instruct-abliterated",
"name": "huihui-ai/Qwen2.5-32B-Instruct-abliterated",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"hunyuan-t1-latest": {
"id": "hunyuan-t1-latest",
"name": "hunyuan-t1-latest",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"hunyuan-turbos-20250226": {
"id": "hunyuan-turbos-20250226",
"name": "hunyuan-turbos-20250226",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"ibm-granite/granite-4.1-8b": {
"id": "ibm-granite/granite-4.1-8b",
"name": "Granite 4.1 8B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.05,
"output": 0.1,
"cacheRead": 0.05,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072
},
"inclusionai/ling-2.6-1t": {
"id": "inclusionai/ling-2.6-1t",
"name": "Ling 2.6 1T",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 2.5,
"cacheRead": 0.06,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768
},
"inclusionai/ling-2.6-flash": {
"id": "inclusionai/ling-2.6-flash",
"name": "Ling 2.6 Flash",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.08,
"output": 0.24,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768
},
"inclusionai/ring-2.6-1t": {
"id": "inclusionai/ring-2.6-1t",
"name": "Ring 2.6 1T",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"Infermatic/MN-12B-Inferor-v0.0": {
"id": "Infermatic/MN-12B-Inferor-v0.0",
"name": "Infermatic/MN-12B-Inferor-v0.0",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"inflatebot/MN-12B-Mag-Mell-R1": {
"id": "inflatebot/MN-12B-Mag-Mell-R1",
"name": "inflatebot/MN-12B-Mag-Mell-R1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"inflection/inflection-3-pi": {
"id": "inflection/inflection-3-pi",
"name": "inflection/inflection-3-pi",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"inflection/inflection-3-productivity": {
"id": "inflection/inflection-3-productivity",
"name": "inflection/inflection-3-productivity",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"jamba-large": {
"id": "jamba-large",
"name": "jamba-large",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"jamba-large-1.6": {
"id": "jamba-large-1.6",
"name": "jamba-large-1.6",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"jamba-large-1.7": {
"id": "jamba-large-1.7",
"name": "jamba-large-1.7",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 4096
},
"jamba-mini": {
"id": "jamba-mini",
"name": "jamba-mini",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"jamba-mini-1.6": {
"id": "jamba-mini-1.6",
"name": "jamba-mini-1.6",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"jamba-mini-1.7": {
"id": "jamba-mini-1.7",
"name": "jamba-mini-1.7",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"KAT-Coder-Air-V1": {
"id": "KAT-Coder-Air-V1",
"name": "KAT-Coder-Air-V1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"KAT-Coder-Exp-72B-1010": {
"id": "KAT-Coder-Exp-72B-1010",
"name": "KAT-Coder-Exp-72B-1010",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"KAT-Coder-Pro-V1": {
"id": "KAT-Coder-Pro-V1",
"name": "KAT-Coder-Pro-V1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"kimi-k2-instruct-fast": {
"id": "kimi-k2-instruct-fast",
"name": "kimi-k2-instruct-fast",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"kimi-thinking-preview": {
"id": "kimi-thinking-preview",
"name": "kimi-thinking-preview",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"kwaipilot/kat-coder-pro-v2": {
"id": "kwaipilot/kat-coder-pro-v2",
"name": "KAT-Coder-Pro V2",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.06,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 80000
},
"LatitudeGames/Wayfarer-Large-70B-Llama-3.3": {
"id": "LatitudeGames/Wayfarer-Large-70B-Llama-3.3",
"name": "LatitudeGames/Wayfarer-Large-70B-Llama-3.3",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"learnlm-1.5-pro-experimental": {
"id": "learnlm-1.5-pro-experimental",
"name": "learnlm-1.5-pro-experimental",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"linkup-research-high": {
"id": "linkup-research-high",
"name": "linkup-research-high",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"linkup-research-low": {
"id": "linkup-research-low",
"name": "linkup-research-low",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"linkup-research-medium": {
"id": "linkup-research-medium",
"name": "linkup-research-medium",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"linkup-research-xhigh": {
"id": "linkup-research-xhigh",
"name": "linkup-research-xhigh",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"liquid/lfm-2-24b-a2b": {
"id": "liquid/lfm-2-24b-a2b",
"name": "liquid/lfm-2-24b-a2b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-Anthrobomination": {
"id": "Llama-3.3-70B-Anthrobomination",
"name": "Llama-3.3-70B-Anthrobomination",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-Argunaut-1-SFT": {
"id": "Llama-3.3-70B-Argunaut-1-SFT",
"name": "Llama-3.3-70B-Argunaut-1-SFT",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-ArliAI-RPMax-v1.4": {
"id": "Llama-3.3-70B-ArliAI-RPMax-v1.4",
"name": "Llama-3.3-70B-ArliAI-RPMax-v1.4",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-ArliAI-RPMax-v2": {
"id": "Llama-3.3-70B-ArliAI-RPMax-v2",
"name": "Llama-3.3-70B-ArliAI-RPMax-v2",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-ArliAI-RPMax-v3": {
"id": "Llama-3.3-70B-ArliAI-RPMax-v3",
"name": "Llama-3.3-70B-ArliAI-RPMax-v3",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-Aurora-Borealis": {
"id": "Llama-3.3-70B-Aurora-Borealis",
"name": "Llama-3.3-70B-Aurora-Borealis",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-Bigger-Body": {
"id": "Llama-3.3-70B-Bigger-Body",
"name": "Llama-3.3-70B-Bigger-Body",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-Cirrus-x1": {
"id": "Llama-3.3-70B-Cirrus-x1",
"name": "Llama-3.3-70B-Cirrus-x1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-Cu-Mai-R1": {
"id": "Llama-3.3-70B-Cu-Mai-R1",
"name": "Llama-3.3-70B-Cu-Mai-R1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-Damascus-R1": {
"id": "Llama-3.3-70B-Damascus-R1",
"name": "Llama-3.3-70B-Damascus-R1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-Dark-Ages-v0.1": {
"id": "Llama-3.3-70B-Dark-Ages-v0.1",
"name": "Llama-3.3-70B-Dark-Ages-v0.1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-Electra-R1": {
"id": "Llama-3.3-70B-Electra-R1",
"name": "Llama-3.3-70B-Electra-R1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-Electranova-v1.0": {
"id": "Llama-3.3-70B-Electranova-v1.0",
"name": "Llama-3.3-70B-Electranova-v1.0",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-Fallen-R1-v1": {
"id": "Llama-3.3-70B-Fallen-R1-v1",
"name": "Llama-3.3-70B-Fallen-R1-v1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-Fallen-v1": {
"id": "Llama-3.3-70B-Fallen-v1",
"name": "Llama-3.3-70B-Fallen-v1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-Forgotten-Abomination-v5.0": {
"id": "Llama-3.3-70B-Forgotten-Abomination-v5.0",
"name": "Llama-3.3-70B-Forgotten-Abomination-v5.0",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-Forgotten-Safeword-3.6": {
"id": "Llama-3.3-70B-Forgotten-Safeword-3.6",
"name": "Llama-3.3-70B-Forgotten-Safeword-3.6",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-GeneticLemonade-Opus": {
"id": "Llama-3.3-70B-GeneticLemonade-Opus",
"name": "Llama-3.3-70B-GeneticLemonade-Opus",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-GeneticLemonade-Unleashed-v3": {
"id": "Llama-3.3-70B-GeneticLemonade-Unleashed-v3",
"name": "Llama-3.3-70B-GeneticLemonade-Unleashed-v3",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-Ignition-v0.1": {
"id": "Llama-3.3-70B-Ignition-v0.1",
"name": "Llama-3.3-70B-Ignition-v0.1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-Incandescent-Malevolence": {
"id": "Llama-3.3-70B-Incandescent-Malevolence",
"name": "Llama-3.3-70B-Incandescent-Malevolence",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-Legion-V2.1": {
"id": "Llama-3.3-70B-Legion-V2.1",
"name": "Llama-3.3-70B-Legion-V2.1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-Magnum-v4-SE": {
"id": "Llama-3.3-70B-Magnum-v4-SE",
"name": "Llama-3.3-70B-Magnum-v4-SE",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-Magnum-v4-SE-Cirrus-x1-SLERP": {
"id": "Llama-3.3-70B-Magnum-v4-SE-Cirrus-x1-SLERP",
"name": "Llama-3.3-70B-Magnum-v4-SE-Cirrus-x1-SLERP",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-Mhnnn-x1": {
"id": "Llama-3.3-70B-Mhnnn-x1",
"name": "Llama-3.3-70B-Mhnnn-x1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-MiraiFanfare": {
"id": "Llama-3.3-70B-MiraiFanfare",
"name": "Llama-3.3-70B-MiraiFanfare",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-Mokume-Gane-R1": {
"id": "Llama-3.3-70B-Mokume-Gane-R1",
"name": "Llama-3.3-70B-Mokume-Gane-R1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-MS-Nevoria": {
"id": "Llama-3.3-70B-MS-Nevoria",
"name": "Llama-3.3-70B-MS-Nevoria",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-Nova": {
"id": "Llama-3.3-70B-Nova",
"name": "Llama-3.3-70B-Nova",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-Predatorial-Extasy": {
"id": "Llama-3.3-70B-Predatorial-Extasy",
"name": "Llama-3.3-70B-Predatorial-Extasy",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-Progenitor-V3.3": {
"id": "Llama-3.3-70B-Progenitor-V3.3",
"name": "Llama-3.3-70B-Progenitor-V3.3",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-RAWMAW": {
"id": "Llama-3.3-70B-RAWMAW",
"name": "Llama-3.3-70B-RAWMAW",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-Sapphira-0.1": {
"id": "Llama-3.3-70B-Sapphira-0.1",
"name": "Llama-3.3-70B-Sapphira-0.1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-Sapphira-0.2": {
"id": "Llama-3.3-70B-Sapphira-0.2",
"name": "Llama-3.3-70B-Sapphira-0.2",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-Shakudo": {
"id": "Llama-3.3-70B-Shakudo",
"name": "Llama-3.3-70B-Shakudo",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-StrawberryLemonade-v1.0": {
"id": "Llama-3.3-70B-StrawberryLemonade-v1.0",
"name": "Llama-3.3-70B-StrawberryLemonade-v1.0",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-Strawberrylemonade-v1.2": {
"id": "Llama-3.3-70B-Strawberrylemonade-v1.2",
"name": "Llama-3.3-70B-Strawberrylemonade-v1.2",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-The-Omega-Directive-Unslop-v2.0": {
"id": "Llama-3.3-70B-The-Omega-Directive-Unslop-v2.0",
"name": "Llama-3.3-70B-The-Omega-Directive-Unslop-v2.0",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-The-Omega-Directive-Unslop-v2.1": {
"id": "Llama-3.3-70B-The-Omega-Directive-Unslop-v2.1",
"name": "Llama-3.3-70B-The-Omega-Directive-Unslop-v2.1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3-70B-Vulpecula-R1": {
"id": "Llama-3.3-70B-Vulpecula-R1",
"name": "Llama-3.3-70B-Vulpecula-R1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3+(3.1v3.3)-70B-Hanami-x1": {
"id": "Llama-3.3+(3.1v3.3)-70B-Hanami-x1",
"name": "Llama-3.3+(3.1v3.3)-70B-Hanami-x1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3+(3.1v3.3)-70B-New-Dawn-v1.1": {
"id": "Llama-3.3+(3.1v3.3)-70B-New-Dawn-v1.1",
"name": "Llama-3.3+(3.1v3.3)-70B-New-Dawn-v1.1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Llama-3.3+(3v3.3)-70B-TenyxChat-DaybreakStorywriter": {
"id": "Llama-3.3+(3v3.3)-70B-TenyxChat-DaybreakStorywriter",
"name": "Llama-3.3+(3v3.3)-70B-TenyxChat-DaybreakStorywriter",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"LLM360/K2-Think": {
"id": "LLM360/K2-Think",
"name": "LLM360/K2-Think",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Magistral-Small-2506": {
"id": "Magistral-Small-2506",
"name": "Magistral-Small-2506",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"MarinaraSpaghetti/NemoMix-Unleashed-12B": {
"id": "MarinaraSpaghetti/NemoMix-Unleashed-12B",
"name": "MarinaraSpaghetti/NemoMix-Unleashed-12B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"meganova-ai/manta-flash-1.0": {
"id": "meganova-ai/manta-flash-1.0",
"name": "meganova-ai/manta-flash-1.0",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"meganova-ai/manta-mini-1.0": {
"id": "meganova-ai/manta-mini-1.0",
"name": "meganova-ai/manta-mini-1.0",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"meganova-ai/manta-pro-1.0": {
"id": "meganova-ai/manta-pro-1.0",
"name": "meganova-ai/manta-pro-1.0",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"meituan-longcat/LongCat-Flash-Chat-FP8": {
"id": "meituan-longcat/LongCat-Flash-Chat-FP8",
"name": "meituan-longcat/LongCat-Flash-Chat-FP8",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"mercury-2": {
"id": "mercury-2",
"name": "Mercury 2",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.25,
"output": 0.75,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 50000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"mercury-coder-small": {
"id": "mercury-coder-small",
"name": "mercury-coder-small",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Meta-Llama-3-1-8B-Instruct-FP8": {
"id": "Meta-Llama-3-1-8B-Instruct-FP8",
"name": "Meta-Llama-3-1-8B-Instruct-FP8",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"meta-llama/llama-3.1-8b-instruct": {
"id": "meta-llama/llama-3.1-8b-instruct",
"name": "Llama 3.1 8B Instruct",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.02,
"output": 0.049999999999999996,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384
},
"meta-llama/llama-3.2-3b-instruct": {
"id": "meta-llama/llama-3.2-3b-instruct",
"name": "meta-llama/llama-3.2-3b-instruct",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"meta-llama/llama-3.3-70b-instruct": {
"id": "meta-llama/llama-3.3-70b-instruct",
"name": "Llama 3.3 70b Instruct",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.05,
"output": 0.23,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384
},
"meta-llama/llama-4-maverick": {
"id": "meta-llama/llama-4-maverick",
"name": "Llama 4 Maverick",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.18000000000000002,
"output": 0.8,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536
},
"meta-llama/llama-4-scout": {
"id": "meta-llama/llama-4-scout",
"name": "Llama 4 Scout",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.085,
"output": 0.46,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 328000,
"maxTokens": 65536
},
"microsoft/MAI-DS-R1-FP8": {
"id": "microsoft/MAI-DS-R1-FP8",
"name": "microsoft/MAI-DS-R1-FP8",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"microsoft/wizardlm-2-8x22b": {
"id": "microsoft/wizardlm-2-8x22b",
"name": "microsoft/wizardlm-2-8x22b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"MiniMax-M1": {
"id": "MiniMax-M1",
"name": "MiniMax-M1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 40000
},
"MiniMax-M2": {
"id": "MiniMax-M2",
"name": "MiniMax-M2",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 196608,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
},
"compat": {
"supportsDeveloperRole": false,
"thinkingFormat": "zai",
"reasoningContentField": "reasoning_content"
}
},
"minimax/minimax-01": {
"id": "minimax/minimax-01",
"name": "minimax/minimax-01",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"minimax/minimax-latest": {
"id": "minimax/minimax-latest",
"name": "MiniMax Latest",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.06,
"cacheWrite": 0
},
"contextWindow": 512000,
"maxTokens": 80000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"minimax/minimax-m2-her": {
"id": "minimax/minimax-m2-her",
"name": "minimax/minimax-m2-her",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 64000,
"maxTokens": null
},
"minimax/minimax-m2.1": {
"id": "minimax/minimax-m2.1",
"name": "MiniMax M2.1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.33,
"output": 1.32,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax/minimax-m2.5": {
"id": "minimax/minimax-m2.5",
"name": "MiniMax M2.5",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax/minimax-m2.7": {
"id": "minimax/minimax-m2.7",
"name": "MiniMax M2.7",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax/minimax-m2.7-turbo": {
"id": "minimax/minimax-m2.7-turbo",
"name": "MiniMax M2.7 Turbo",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax/minimax-m3": {
"id": "minimax/minimax-m3",
"name": "MiniMax M3",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.06,
"cacheWrite": 0
},
"contextWindow": 512000,
"maxTokens": 80000
},
"minimax/minimax-m3:thinking": {
"id": "minimax/minimax-m3:thinking",
"name": "MiniMax M3 Thinking",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.06,
"cacheWrite": 0
},
"contextWindow": 512000,
"maxTokens": 80000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"MiniMaxAI/MiniMax-M1-80k": {
"id": "MiniMaxAI/MiniMax-M1-80k",
"name": "MiniMaxAI/MiniMax-M1-80k",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"miromind-ai/mirothinker-v1.5-235b": {
"id": "miromind-ai/mirothinker-v1.5-235b",
"name": "miromind-ai/mirothinker-v1.5-235b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"mirothinker-1-7-deepresearch": {
"id": "mirothinker-1-7-deepresearch",
"name": "mirothinker-1-7-deepresearch",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"mirothinker-1-7-deepresearch-mini": {
"id": "mirothinker-1-7-deepresearch-mini",
"name": "mirothinker-1-7-deepresearch-mini",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"mistral-code-agent-latest": {
"id": "mistral-code-agent-latest",
"name": "Mistral Code Agent Latest",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.4,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768
},
"mistral-code-latest": {
"id": "mistral-code-latest",
"name": "Mistral Code Latest",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 0.9,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 32768
},
"Mistral-Nemo-12B-Instruct-2407": {
"id": "Mistral-Nemo-12B-Instruct-2407",
"name": "Mistral-Nemo-12B-Instruct-2407",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"mistral-small-31-24b-instruct": {
"id": "mistral-small-31-24b-instruct",
"name": "mistral-small-31-24b-instruct",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"mistral/mistral-medium-3.5": {
"id": "mistral/mistral-medium-3.5",
"name": "Mistral Medium 3.5",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.5,
"output": 7.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"mistral/mistral-medium-3.5:thinking": {
"id": "mistral/mistral-medium-3.5:thinking",
"name": "Mistral Medium 3.5 Thinking",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.5,
"output": 7.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"mistral/mistral-vibe-cli-latest": {
"id": "mistral/mistral-vibe-cli-latest",
"name": "mistral/mistral-vibe-cli-latest",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"mistralai/codestral-2508": {
"id": "mistralai/codestral-2508",
"name": "Codestral 2508",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 0.8999999999999999,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 4096
},
"mistralai/devstral-2-123b-instruct-2512": {
"id": "mistralai/devstral-2-123b-instruct-2512",
"name": "Devstral-2-123B-Instruct-2512",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"mistralai/Devstral-Small-2505": {
"id": "mistralai/Devstral-Small-2505",
"name": "mistralai/Devstral-Small-2505",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 128000
},
"mistralai/ministral-14b-2512": {
"id": "mistralai/ministral-14b-2512",
"name": "Ministral 3 14B 2512",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.19999999999999998,
"output": 0.19999999999999998,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 4096
},
"mistralai/ministral-14b-instruct-2512": {
"id": "mistralai/ministral-14b-instruct-2512",
"name": "Ministral 3 14B Instruct 2512",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"mistralai/ministral-3b-2512": {
"id": "mistralai/ministral-3b-2512",
"name": "Ministral 3 3B 2512",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.09999999999999999,
"output": 0.09999999999999999,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768
},
"mistralai/ministral-8b-2512": {
"id": "mistralai/ministral-8b-2512",
"name": "Ministral 3 8B 2512",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 0.15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 4096
},
"mistralai/mistral-7b-instruct": {
"id": "mistralai/mistral-7b-instruct",
"name": "mistralai/mistral-7b-instruct",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"mistralai/mistral-large": {
"id": "mistralai/mistral-large",
"name": "Mistral Large",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 2,
"output": 6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 25600
},
"mistralai/mistral-large-3-675b-instruct-2512": {
"id": "mistralai/mistral-large-3-675b-instruct-2512",
"name": "Mistral Large 3 675B Instruct 2512",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"mistralai/mistral-medium-3": {
"id": "mistralai/mistral-medium-3",
"name": "Mistral Medium 3",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.39999999999999997,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 26215
},
"mistralai/mistral-medium-3.1": {
"id": "mistralai/mistral-medium-3.1",
"name": "Mistral Medium 3.1",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.39999999999999997,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 26215
},
"mistralai/Mistral-Nemo-Instruct-2407": {
"id": "mistralai/Mistral-Nemo-Instruct-2407",
"name": "mistralai/Mistral-Nemo-Instruct-2407",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"mistralai/mistral-saba": {
"id": "mistralai/mistral-saba",
"name": "Saba",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.19999999999999998,
"output": 0.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32768,
"maxTokens": 32768
},
"mistralai/mistral-small-4-119b-2603": {
"id": "mistralai/mistral-small-4-119b-2603",
"name": "Mistral Small 4 119B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.4,
"output": 1.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"mistralai/mistral-small-4-119b-2603:thinking": {
"id": "mistralai/mistral-small-4-119b-2603:thinking",
"name": "Mistral Small 4 119B Thinking",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.4,
"output": 1.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"mistralai/mistral-small-creative": {
"id": "mistralai/mistral-small-creative",
"name": "Mistral Small Creative",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.09999999999999999,
"output": 0.3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"mistralai/mistral-tiny": {
"id": "mistralai/mistral-tiny",
"name": "mistralai/mistral-tiny",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"mistralai/mixtral-8x22b-instruct-v0.1": {
"id": "mistralai/mixtral-8x22b-instruct-v0.1",
"name": "mistralai/mixtral-8x22b-instruct-v0.1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"mistralai/mixtral-8x7b-instruct-v0.1": {
"id": "mistralai/mixtral-8x7b-instruct-v0.1",
"name": "mistralai/mixtral-8x7b-instruct-v0.1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"mlabonne/NeuralDaredevil-8B-abliterated": {
"id": "mlabonne/NeuralDaredevil-8B-abliterated",
"name": "mlabonne/NeuralDaredevil-8B-abliterated",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"moonshotai/Kimi-Dev-72B": {
"id": "moonshotai/Kimi-Dev-72B",
"name": "moonshotai/Kimi-Dev-72B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"moonshotai/kimi-k2-instruct": {
"id": "moonshotai/kimi-k2-instruct",
"name": "Kimi K2 Instruct",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.1,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 8192
},
"moonshotai/kimi-k2-instruct-0711": {
"id": "moonshotai/kimi-k2-instruct-0711",
"name": "Kimi K2 0711",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.1,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"moonshotai/Kimi-K2-Instruct-0905": {
"id": "moonshotai/Kimi-K2-Instruct-0905",
"name": "Kimi K2 0905",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.4,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 262144
},
"moonshotai/kimi-k2-thinking": {
"id": "moonshotai/kimi-k2-thinking",
"name": "Kimi K2 Thinking",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 262144
},
"moonshotai/kimi-k2-thinking-original": {
"id": "moonshotai/kimi-k2-thinking-original",
"name": "moonshotai/kimi-k2-thinking-original",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"moonshotai/kimi-k2-thinking-turbo-original": {
"id": "moonshotai/kimi-k2-thinking-turbo-original",
"name": "moonshotai/kimi-k2-thinking-turbo-original",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262000,
"maxTokens": 64000
},
"moonshotai/kimi-k2.5": {
"id": "moonshotai/kimi-k2.5",
"name": "Kimi K2.5",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 1.9,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 65536
},
"moonshotai/kimi-k2.5:thinking": {
"id": "moonshotai/kimi-k2.5:thinking",
"name": "Kimi K2.5 Thinking",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 1.9,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"moonshotai/kimi-k2.6": {
"id": "moonshotai/kimi-k2.6",
"name": "Kimi K2.6",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.53,
"output": 2.73,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 65536
},
"moonshotai/kimi-k2.6:thinking": {
"id": "moonshotai/kimi-k2.6:thinking",
"name": "Kimi K2.6 Thinking",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.53,
"output": 2.73,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"moonshotai/kimi-k2.7-code": {
"id": "moonshotai/kimi-k2.7-code",
"name": "Kimi K2.7 Code",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"moonshotai/kimi-k2.7-code-highspeed": {
"id": "moonshotai/kimi-k2.7-code-highspeed",
"name": "moonshotai/kimi-k2.7-code-highspeed",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"moonshotai/kimi-latest": {
"id": "moonshotai/kimi-latest",
"name": "Kimi Latest",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.5,
"output": 2.6,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nanogpt/coding-router": {
"id": "nanogpt/coding-router",
"name": "Coding Router",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.1,
"output": 2.2,
"cacheRead": 0.11,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nanogpt/coding-router:high": {
"id": "nanogpt/coding-router:high",
"name": "Coding Router High",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.1,
"output": 2.2,
"cacheRead": 0.11,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nanogpt/coding-router:low": {
"id": "nanogpt/coding-router:low",
"name": "Coding Router Low",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.14,
"output": 0.28,
"cacheRead": 0.028,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nanogpt/coding-router:max": {
"id": "nanogpt/coding-router:max",
"name": "Coding Router Max",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 5,
"output": 30,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nanogpt/coding-router:medium": {
"id": "nanogpt/coding-router:medium",
"name": "Coding Router Medium",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.14,
"output": 0.28,
"cacheRead": 0.028,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"NeverSleep/Llama-3-Lumimaid-70B-v0.1": {
"id": "NeverSleep/Llama-3-Lumimaid-70B-v0.1",
"name": "NeverSleep/Llama-3-Lumimaid-70B-v0.1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"NeverSleep/Lumimaid-v0.2-70B": {
"id": "NeverSleep/Lumimaid-v0.2-70B",
"name": "NeverSleep/Lumimaid-v0.2-70B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nex-agi/deepseek-v3.1-nex-n1": {
"id": "nex-agi/deepseek-v3.1-nex-n1",
"name": "DeepSeek V3.1 Nex N1",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.27,
"output": 1,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 163840
},
"nex-agi/nex-n2-pro": {
"id": "nex-agi/nex-n2-pro",
"name": "nex-agi/nex-n2-pro",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nothingiisreal/L3.1-70B-Celeste-V0.1-BF16": {
"id": "nothingiisreal/L3.1-70B-Celeste-V0.1-BF16",
"name": "nothingiisreal/L3.1-70B-Celeste-V0.1-BF16",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"NousResearch/DeepHermes-3-Mistral-24B-Preview": {
"id": "NousResearch/DeepHermes-3-Mistral-24B-Preview",
"name": "NousResearch/DeepHermes-3-Mistral-24B-Preview",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nousresearch/hermes-3-llama-3.1-70b": {
"id": "nousresearch/hermes-3-llama-3.1-70b",
"name": "nousresearch/hermes-3-llama-3.1-70b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"nousresearch/hermes-4-405b": {
"id": "nousresearch/hermes-4-405b",
"name": "nousresearch/hermes-4-405b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nousresearch/hermes-4-70b": {
"id": "nousresearch/hermes-4-70b",
"name": "Hermes 4 70B",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.11,
"output": 0.38,
"cacheRead": 0.055,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nvidia/Llama-3_3-Nemotron-Super-49B-v1_5": {
"id": "nvidia/Llama-3_3-Nemotron-Super-49B-v1_5",
"name": "nvidia/Llama-3_3-Nemotron-Super-49B-v1_5",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072
},
"nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": {
"id": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
"name": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/Llama-3.1-Nemotron-Ultra-253B-v1": {
"id": "nvidia/Llama-3.1-Nemotron-Ultra-253B-v1",
"name": "nvidia/Llama-3.1-Nemotron-Ultra-253B-v1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192
},
"nvidia/Llama-3.3-Nemotron-Super-49B-v1": {
"id": "nvidia/Llama-3.3-Nemotron-Super-49B-v1",
"name": "nvidia/Llama-3.3-Nemotron-Super-49B-v1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/nemotron-3-nano-30b-a3b": {
"id": "nvidia/nemotron-3-nano-30b-a3b",
"name": "Nemotron 3 Nano 30B A3B",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.049999999999999996,
"output": 0.19999999999999998,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning": {
"id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
"name": "Nvidia Nemotron 3 Nano Omni",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.105,
"output": 0.42,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"nvidia/nemotron-3-super-120b-a12b": {
"id": "nvidia/nemotron-3-super-120b-a12b",
"name": "Nvidia Nemotron 3 Super 120B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.05,
"output": 0.25,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nvidia/nemotron-3-super-120b-a12b:thinking": {
"id": "nvidia/nemotron-3-super-120b-a12b:thinking",
"name": "Nvidia Nemotron 3 Super 120B Thinking",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.05,
"output": 0.25,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nvidia/nemotron-3-ultra-550b-a55b": {
"id": "nvidia/nemotron-3-ultra-550b-a55b",
"name": "Nemotron 3 Ultra 550B A55B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-TEE": {
"id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-TEE",
"name": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-TEE",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/nvidia-nemotron-nano-9b-v2": {
"id": "nvidia/nvidia-nemotron-nano-9b-v2",
"name": "nvidia-nemotron-nano-9b-v2",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/chatgpt-4o-latest": {
"id": "openai/chatgpt-4o-latest",
"name": "openai/chatgpt-4o-latest",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"openai/gpt-3.5-turbo": {
"id": "openai/gpt-3.5-turbo",
"name": "GPT-3.5 Turbo",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.5,
"output": 1.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 16385,
"maxTokens": 4096
},
"openai/gpt-4-turbo": {
"id": "openai/gpt-4-turbo",
"name": "GPT-4 Turbo",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 10,
"output": 30,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"openai/gpt-4-turbo-preview": {
"id": "openai/gpt-4-turbo-preview",
"name": "GPT-4 Turbo Preview",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 10,
"output": 30,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"openai/gpt-4.1": {
"id": "openai/gpt-4.1",
"name": "GPT 4.1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 8,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1047576,
"maxTokens": 32768
},
"openai/gpt-4.1-mini": {
"id": "openai/gpt-4.1-mini",
"name": "GPT-4.1 Mini",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.39999999999999997,
"output": 1.5999999999999999,
"cacheRead": 0.09999999999999999,
"cacheWrite": 0
},
"contextWindow": 1047576,
"maxTokens": 32768
},
"openai/gpt-4.1-nano": {
"id": "openai/gpt-4.1-nano",
"name": "GPT-4.1 Nano",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.09999999999999999,
"output": 0.39999999999999997,
"cacheRead": 0.024999999999999998,
"cacheWrite": 0
},
"contextWindow": 1047576,
"maxTokens": 32768
},
"openai/gpt-4o": {
"id": "openai/gpt-4o",
"name": "GPT-4o",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 10,
"cacheRead": 1.25,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-4o-2024-08-06": {
"id": "openai/gpt-4o-2024-08-06",
"name": "GPT-4o (2024-08-06)",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 10,
"cacheRead": 1.25,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-4o-2024-11-20": {
"id": "openai/gpt-4o-2024-11-20",
"name": "GPT-4o (2024-11-20)",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 10,
"cacheRead": 1.25,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-4o-mini": {
"id": "openai/gpt-4o-mini",
"name": "GPT-4o mini",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0.075,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-4o-mini-search-preview": {
"id": "openai/gpt-4o-mini-search-preview",
"name": "openai/gpt-4o-mini-search-preview",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"openai/gpt-4o-search-preview": {
"id": "openai/gpt-4o-search-preview",
"name": "openai/gpt-4o-search-preview",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"openai/gpt-5": {
"id": "openai/gpt-5",
"name": "GPT 5",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5-chat-latest": {
"id": "openai/gpt-5-chat-latest",
"name": "openai/gpt-5-chat-latest",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-5-codex": {
"id": "openai/gpt-5-codex",
"name": "GPT-5 Codex",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5-mini": {
"id": "openai/gpt-5-mini",
"name": "GPT-5 Mini",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 2,
"cacheRead": 0.024999999999999998,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5-nano": {
"id": "openai/gpt-5-nano",
"name": "GPT-5 Nano",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.049999999999999996,
"output": 0.39999999999999997,
"cacheRead": 0.005,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5-pro": {
"id": "openai/gpt-5-pro",
"name": "GPT-5 Pro",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 120,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5.1": {
"id": "openai/gpt-5.1",
"name": "GPT 5.1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5.1-2025-11-13": {
"id": "openai/gpt-5.1-2025-11-13",
"name": "openai/gpt-5.1-2025-11-13",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-5.1-chat": {
"id": "openai/gpt-5.1-chat",
"name": "GPT-5.1 Chat",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 64000
},
"openai/gpt-5.1-chat-latest": {
"id": "openai/gpt-5.1-chat-latest",
"name": "openai/gpt-5.1-chat-latest",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-5.1-codex": {
"id": "openai/gpt-5.1-codex",
"name": "GPT-5.1 Codex",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5.1-codex-max": {
"id": "openai/gpt-5.1-codex-max",
"name": "GPT 5.1 Codex Max",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 20,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5.1-codex-mini": {
"id": "openai/gpt-5.1-codex-mini",
"name": "GPT-5.1-Codex-Mini",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 2,
"cacheRead": 0.024999999999999998,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"medium",
"high"
]
}
},
"openai/gpt-5.2": {
"id": "openai/gpt-5.2",
"name": "GPT 5.2",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.2-chat": {
"id": "openai/gpt-5.2-chat",
"name": "GPT-5.2 Chat",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-5.2-codex": {
"id": "openai/gpt-5.2-codex",
"name": "GPT 5.2 Codex",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.2-pro": {
"id": "openai/gpt-5.2-pro",
"name": "GPT 5.2 Pro",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 21,
"output": 168,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.3-chat": {
"id": "openai/gpt-5.3-chat",
"name": "GPT-5.3 Chat",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16380
},
"openai/gpt-5.3-codex": {
"id": "openai/gpt-5.3-codex",
"name": "GPT 5.3 Codex",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.4": {
"id": "openai/gpt-5.4",
"name": "GPT 5.4",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 15,
"cacheRead": 0.25,
"cacheWrite": 0
},
"contextWindow": 922000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.4-mini": {
"id": "openai/gpt-5.4-mini",
"name": "GPT 5.4 Mini",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.75,
"output": 4.5,
"cacheRead": 0.075,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.4-nano": {
"id": "openai/gpt-5.4-nano",
"name": "GPT 5.4 Nano",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.2,
"output": 1.25,
"cacheRead": 0.02,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.4-pro": {
"id": "openai/gpt-5.4-pro",
"name": "GPT 5.4 Pro",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 30,
"output": 180,
"cacheRead": 3,
"cacheWrite": 0
},
"contextWindow": 922000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.5": {
"id": "openai/gpt-5.5",
"name": "GPT 5.5",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 30,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
},
"contextPromotionTarget": "nanogpt/openai/gpt-5.4"
},
"openai/gpt-chat-latest": {
"id": "openai/gpt-chat-latest",
"name": "GPT Chat Latest",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 30,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000
},
"openai/gpt-latest": {
"id": "openai/gpt-latest",
"name": "GPT Latest",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 30,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-oss-120b": {
"id": "openai/gpt-oss-120b",
"name": "GPT OSS 120B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.05,
"output": 0.25,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
]
}
},
"openai/gpt-oss-20b": {
"id": "openai/gpt-oss-20b",
"name": "GPT OSS 20B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.075,
"output": 0.3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
]
}
},
"openai/gpt-oss-safeguard-20b": {
"id": "openai/gpt-oss-safeguard-20b",
"name": "Safety GPT OSS 20B",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.075,
"output": 0.3,
"cacheRead": 0.037,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
]
}
},
"openai/o1": {
"id": "openai/o1",
"name": "o1",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 60,
"cacheRead": 7.5,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"openai/o1-preview": {
"id": "openai/o1-preview",
"name": "openai/o1-preview",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"openai/o1-pro": {
"id": "openai/o1-pro",
"name": "openai/o1-pro",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000
},
"openai/o3": {
"id": "openai/o3",
"name": "o3",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 8,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"openai/o3-deep-research": {
"id": "openai/o3-deep-research",
"name": "o3 Deep Research",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 10,
"output": 40,
"cacheRead": 2.5,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"openai/o3-mini": {
"id": "openai/o3-mini",
"name": "OpenAI o3-mini",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.1,
"output": 4.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"openai/o3-mini-high": {
"id": "openai/o3-mini-high",
"name": "OpenAI o3-mini (High)",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.64,
"output": 2.588,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"openai/o3-mini-low": {
"id": "openai/o3-mini-low",
"name": "OpenAI o3-mini (Low)",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 9.996,
"output": 19.992,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"openai/o3-pro-2025-06-10": {
"id": "openai/o3-pro-2025-06-10",
"name": "OpenAI o3-pro (2025-06-10)",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 9.996,
"output": 19.992,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"openai/o4-mini": {
"id": "openai/o4-mini",
"name": "OpenAI o4-mini",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.1,
"output": 4.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"openai/o4-mini-deep-research": {
"id": "openai/o4-mini-deep-research",
"name": "o4 Mini Deep Research",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 8,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"openai/o4-mini-high": {
"id": "openai/o4-mini-high",
"name": "OpenAI o4-mini high",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.1,
"output": 4.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"owl": {
"id": "owl",
"name": "OWL",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.1,
"output": 0.3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048756,
"maxTokens": 262144
},
"pamanseau/OpenReasoning-Nemotron-32B": {
"id": "pamanseau/OpenReasoning-Nemotron-32B",
"name": "pamanseau/OpenReasoning-Nemotron-32B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"pangram-ai-detection": {
"id": "pangram-ai-detection",
"name": "pangram-ai-detection",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"pangram-plagiarism-detection": {
"id": "pangram-plagiarism-detection",
"name": "pangram-plagiarism-detection",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"perceptron/perceptron-mk1": {
"id": "perceptron/perceptron-mk1",
"name": "perceptron/perceptron-mk1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"phi-4-mini-instruct": {
"id": "phi-4-mini-instruct",
"name": "phi-4-mini-instruct",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"phi-4-multimodal-instruct": {
"id": "phi-4-multimodal-instruct",
"name": "phi-4-multimodal-instruct",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"poolside/laguna-m.1": {
"id": "poolside/laguna-m.1",
"name": "poolside/laguna-m.1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"poolside/laguna-xs.2": {
"id": "poolside/laguna-xs.2",
"name": "poolside/laguna-xs.2",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"qvq-max": {
"id": "qvq-max",
"name": "qvq-max",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"qwen-3.6-plus": {
"id": "qwen-3.6-plus",
"name": "qwen-3.6-plus",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"qwen-long": {
"id": "qwen-long",
"name": "qwen-long",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"qwen-max": {
"id": "qwen-max",
"name": "qwen-max",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"qwen-plus": {
"id": "qwen-plus",
"name": "qwen-plus",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"qwen-turbo": {
"id": "qwen-turbo",
"name": "qwen-turbo",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"qwen/qwen-2.5-72b-instruct": {
"id": "qwen/qwen-2.5-72b-instruct",
"name": "Qwen2.5 72B Instruct",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.12,
"output": 0.39,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384
},
"Qwen/Qwen2.5-Coder-32B-Instruct": {
"id": "Qwen/Qwen2.5-Coder-32B-Instruct",
"name": "Qwen/Qwen2.5-Coder-32B-Instruct",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"qwen/qwen3-14b": {
"id": "qwen/qwen3-14b",
"name": "Qwen3 14B",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.06,
"output": 0.24,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131702,
"maxTokens": 40960,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3-235b-a22b": {
"id": "qwen/qwen3-235b-a22b",
"name": "Qwen 3 235b A22B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 0.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 41000,
"maxTokens": 32768
},
"Qwen/Qwen3-235B-A22B": {
"id": "Qwen/Qwen3-235B-A22B",
"name": "Qwen/Qwen3-235B-A22B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192
},
"qwen/Qwen3-235B-A22B-Instruct-2507": {
"id": "qwen/Qwen3-235B-A22B-Instruct-2507",
"name": "Qwen 3 235b A22B 2507",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.13,
"output": 0.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 262144
},
"Qwen/Qwen3-235B-A22B-Instruct-2507": {
"id": "Qwen/Qwen3-235B-A22B-Instruct-2507",
"name": "Qwen/Qwen3-235B-A22B-Instruct-2507",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"qwen/Qwen3-235B-A22B-Instruct-2507-TEE": {
"id": "qwen/Qwen3-235B-A22B-Instruct-2507-TEE",
"name": "Qwen 3 235b A22B 2507 (TEE)",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.13,
"output": 0.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 262144
},
"Qwen/Qwen3-235B-A22B-Instruct-2507-TEE": {
"id": "Qwen/Qwen3-235B-A22B-Instruct-2507-TEE",
"name": "Qwen/Qwen3-235B-A22B-Instruct-2507-TEE",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 262144
},
"Qwen/Qwen3-235B-A22B-Thinking-2507": {
"id": "Qwen/Qwen3-235B-A22B-Thinking-2507",
"name": "Qwen3-235B-A22B-Thinking-2507",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"qwen/qwen3-30b-a3b": {
"id": "qwen/qwen3-30b-a3b",
"name": "Qwen3 30B A3B",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.08,
"output": 0.28,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3-32b": {
"id": "qwen/qwen3-32b",
"name": "Qwen3-32B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.29,
"output": 0.59,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 40960,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"Qwen/Qwen3-8B": {
"id": "Qwen/Qwen3-8B",
"name": "Qwen/Qwen3-8B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192
},
"qwen/qwen3-coder": {
"id": "qwen/qwen3-coder",
"name": "Qwen 3 Coder 480B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.13,
"output": 0.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262000,
"maxTokens": 65536
},
"qwen/qwen3-coder-flash": {
"id": "qwen/qwen3-coder-flash",
"name": "Qwen3 Coder Flash",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.5,
"cacheRead": 0.06,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65536
},
"qwen/qwen3-coder-next": {
"id": "qwen/qwen3-coder-next",
"name": "Qwen3 Coder Next",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 1.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536
},
"qwen/qwen3-coder-plus": {
"id": "qwen/qwen3-coder-plus",
"name": "Qwen3 Coder Plus",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 5,
"cacheRead": 0.19999999999999998,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 64000
},
"qwen/qwen3-max": {
"id": "qwen/qwen3-max",
"name": "Qwen3 Max",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 1.2,
"output": 6,
"cacheRead": 0.24,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 64000
},
"qwen/Qwen3-Next-80B-A3B-Instruct": {
"id": "qwen/Qwen3-Next-80B-A3B-Instruct",
"name": "Qwen3 Next 80B A3B (Instruct)",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.65,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 262144
},
"Qwen/Qwen3-Next-80B-A3B-Instruct": {
"id": "Qwen/Qwen3-Next-80B-A3B-Instruct",
"name": "Qwen3-Next-80B-A3B-Instruct",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 16384
},
"qwen/qwen3-next-80b-a3b-thinking": {
"id": "qwen/qwen3-next-80b-a3b-thinking",
"name": "Qwen3 Next 80B A3B Thinking",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"Qwen/Qwen3-VL-235B-A22B-Instruct": {
"id": "Qwen/Qwen3-VL-235B-A22B-Instruct",
"name": "Qwen/Qwen3-VL-235B-A22B-Instruct",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 16384
},
"qwen/qwen3.5-397b-a17b": {
"id": "qwen/qwen3.5-397b-a17b",
"name": "Qwen3.5 397B A17B",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 1,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortRouting": {
"off": "qwen/qwen3.5-397b-a17b",
"minimal": "qwen/qwen3.5-397b-a17b-thinking",
"low": "qwen/qwen3.5-397b-a17b-thinking",
"medium": "qwen/qwen3.5-397b-a17b-thinking",
"high": "qwen/qwen3.5-397b-a17b-thinking"
}
},
"compat": {
"supportsStore": false,
"supportsDeveloperRole": false,
"supportsMultipleSystemMessages": false,
"supportsReasoningEffort": true,
"supportsReasoningParams": true,
"reasoningEffortMap": {},
"supportsUsageInStreaming": true,
"alwaysSendMaxTokens": false,
"disableReasoningOnForcedToolChoice": false,
"disableReasoningOnToolChoice": false,
"supportsToolChoice": true,
"maxTokensField": "max_completion_tokens",
"requiresToolResultName": false,
"requiresAssistantAfterToolResult": false,
"requiresThinkingAsText": false,
"requiresMistralToolIds": false,
"thinkingFormat": "qwen",
"reasoningContentField": "reasoning_content",
"requiresReasoningContentForToolCalls": false,
"allowsSyntheticReasoningContentForToolCalls": true,
"requiresAssistantContentForToolCalls": false,
"isOpenRouterHost": false,
"isVercelGatewayHost": false,
"supportsStrictMode": false,
"toolStrictMode": "mixed"
}
},
"qwen/qwen3.5-9b": {
"id": "qwen/qwen3.5-9b",
"name": "Qwen3.5-9B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.049999999999999996,
"output": 0.15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.5-plus": {
"id": "qwen/qwen3.5-plus",
"name": "Qwen3.5 Plus",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.4,
"output": 2.4,
"cacheRead": 0.04,
"cacheWrite": 0.5
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortRouting": {
"off": "qwen/qwen3.5-plus",
"minimal": "qwen/qwen3.5-plus-thinking",
"low": "qwen/qwen3.5-plus-thinking",
"medium": "qwen/qwen3.5-plus-thinking",
"high": "qwen/qwen3.5-plus-thinking"
}
},
"compat": {
"supportsStore": false,
"supportsDeveloperRole": false,
"supportsMultipleSystemMessages": false,
"supportsReasoningEffort": true,
"supportsReasoningParams": true,
"reasoningEffortMap": {},
"supportsUsageInStreaming": true,
"alwaysSendMaxTokens": false,
"disableReasoningOnForcedToolChoice": false,
"disableReasoningOnToolChoice": false,
"supportsToolChoice": true,
"maxTokensField": "max_completion_tokens",
"requiresToolResultName": false,
"requiresAssistantAfterToolResult": false,
"requiresThinkingAsText": false,
"requiresMistralToolIds": false,
"thinkingFormat": "qwen",
"reasoningContentField": "reasoning_content",
"requiresReasoningContentForToolCalls": false,
"allowsSyntheticReasoningContentForToolCalls": true,
"requiresAssistantContentForToolCalls": false,
"isOpenRouterHost": false,
"isVercelGatewayHost": false,
"supportsStrictMode": false,
"toolStrictMode": "mixed"
}
},
"Qwen/Qwen3.6-35B-A3B": {
"id": "Qwen/Qwen3.6-35B-A3B",
"name": "Qwen/Qwen3.6-35B-A3B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwq-32b-preview": {
"id": "qwen/qwq-32b-preview",
"name": "qwen/qwq-32b-preview",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Qwen2.5-32B-EVA-v0.2": {
"id": "Qwen2.5-32B-EVA-v0.2",
"name": "Qwen2.5-32B-EVA-v0.2",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"qwen25-vl-72b-instruct": {
"id": "qwen25-vl-72b-instruct",
"name": "qwen25-vl-72b-instruct",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"qwen3-30b-a3b-instruct-2507": {
"id": "qwen3-30b-a3b-instruct-2507",
"name": "qwen3-30b-a3b-instruct-2507",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32000
},
"qwen3-coder-30b-a3b-instruct": {
"id": "qwen3-coder-30b-a3b-instruct",
"name": "Qwen3 Coder 30B A3B Instruct",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.1,
"output": 0.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 65536
},
"qwen3-max-2026-01-23": {
"id": "qwen3-max-2026-01-23",
"name": "Qwen3 Max",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768
},
"qwen3-vl-235b-a22b-instruct-original": {
"id": "qwen3-vl-235b-a22b-instruct-original",
"name": "qwen3-vl-235b-a22b-instruct-original",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"qwen3-vl-235b-a22b-thinking": {
"id": "qwen3-vl-235b-a22b-thinking",
"name": "qwen3-vl-235b-a22b-thinking",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 8192
},
"qwen3.5-122b-a10b": {
"id": "qwen3.5-122b-a10b",
"name": "qwen3.5-122b-a10b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen3.5-27b": {
"id": "qwen3.5-27b",
"name": "qwen3.5-27b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"Qwen3.5-27B-Anko": {
"id": "Qwen3.5-27B-Anko",
"name": "Qwen3.5-27B-Anko",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Qwen3.5-27B-BlueStar-Derestricted": {
"id": "Qwen3.5-27B-BlueStar-Derestricted",
"name": "Qwen3.5-27B-BlueStar-Derestricted",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Qwen3.5-27B-BlueStar-Derestricted-Lite": {
"id": "Qwen3.5-27B-BlueStar-Derestricted-Lite",
"name": "Qwen3.5-27B-BlueStar-Derestricted-Lite",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Qwen3.5-27B-BlueStar-v2-Derestricted": {
"id": "Qwen3.5-27B-BlueStar-v2-Derestricted",
"name": "Qwen3.5-27B-BlueStar-v2-Derestricted",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Qwen3.5-27B-BlueStar-v2-Derestricted-Lite": {
"id": "Qwen3.5-27B-BlueStar-v2-Derestricted-Lite",
"name": "Qwen3.5-27B-BlueStar-v2-Derestricted-Lite",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Qwen3.5-27B-BlueStar-v3-Derestricted": {
"id": "Qwen3.5-27B-BlueStar-v3-Derestricted",
"name": "Qwen3.5-27B-BlueStar-v3-Derestricted",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Qwen3.5-27B-BlueStar-v3-Derestricted-Lite": {
"id": "Qwen3.5-27B-BlueStar-v3-Derestricted-Lite",
"name": "Qwen3.5-27B-BlueStar-v3-Derestricted-Lite",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Qwen3.5-27B-Derestricted": {
"id": "Qwen3.5-27B-Derestricted",
"name": "Qwen3.5-27B-Derestricted",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Qwen3.5-27B-earica-Derestricted": {
"id": "Qwen3.5-27B-earica-Derestricted",
"name": "Qwen3.5-27B-earica-Derestricted",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Qwen3.5-27B-earica-Derestricted-Lite": {
"id": "Qwen3.5-27B-earica-Derestricted-Lite",
"name": "Qwen3.5-27B-earica-Derestricted-Lite",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Qwen3.5-27B-Infracelestial": {
"id": "Qwen3.5-27B-Infracelestial",
"name": "Qwen3.5-27B-Infracelestial",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Qwen3.5-27B-Marvin-DPO-V2-Derestricted": {
"id": "Qwen3.5-27B-Marvin-DPO-V2-Derestricted",
"name": "Qwen3.5-27B-Marvin-DPO-V2-Derestricted",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Qwen3.5-27B-Marvin-DPO-V2-Derestricted-Lite": {
"id": "Qwen3.5-27B-Marvin-DPO-V2-Derestricted-Lite",
"name": "Qwen3.5-27B-Marvin-DPO-V2-Derestricted-Lite",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Qwen3.5-27B-Marvin-V2-Derestricted": {
"id": "Qwen3.5-27B-Marvin-V2-Derestricted",
"name": "Qwen3.5-27B-Marvin-V2-Derestricted",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Qwen3.5-27B-Marvin-V2-Derestricted-Lite": {
"id": "Qwen3.5-27B-Marvin-V2-Derestricted-Lite",
"name": "Qwen3.5-27B-Marvin-V2-Derestricted-Lite",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Qwen3.5-27B-Musica-v1": {
"id": "Qwen3.5-27B-Musica-v1",
"name": "Qwen3.5-27B-Musica-v1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Qwen3.5-27B-NaNovel-Derestricted": {
"id": "Qwen3.5-27B-NaNovel-Derestricted",
"name": "Qwen3.5-27B-NaNovel-Derestricted",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Qwen3.5-27B-NaNovel-Derestricted-Lite": {
"id": "Qwen3.5-27B-NaNovel-Derestricted-Lite",
"name": "Qwen3.5-27B-NaNovel-Derestricted-Lite",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Qwen3.5-27B-Omega-Evolution-v2.0-Derestricted": {
"id": "Qwen3.5-27B-Omega-Evolution-v2.0-Derestricted",
"name": "Qwen3.5-27B-Omega-Evolution-v2.0-Derestricted",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Qwen3.5-27B-Omega-Evolution-v2.0-Derestricted-Lite": {
"id": "Qwen3.5-27B-Omega-Evolution-v2.0-Derestricted-Lite",
"name": "Qwen3.5-27B-Omega-Evolution-v2.0-Derestricted-Lite",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Qwen3.5-27B-Omega-Evolution-v2.2-Derestricted": {
"id": "Qwen3.5-27B-Omega-Evolution-v2.2-Derestricted",
"name": "Qwen3.5-27B-Omega-Evolution-v2.2-Derestricted",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Qwen3.5-27B-Omega-Evolution-v2.2-Derestricted-Lite": {
"id": "Qwen3.5-27B-Omega-Evolution-v2.2-Derestricted-Lite",
"name": "Qwen3.5-27B-Omega-Evolution-v2.2-Derestricted-Lite",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Qwen3.5-27B-Queen-Derestricted": {
"id": "Qwen3.5-27B-Queen-Derestricted",
"name": "Qwen3.5-27B-Queen-Derestricted",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Qwen3.5-27B-Queen-Derestricted-Lite": {
"id": "Qwen3.5-27B-Queen-Derestricted-Lite",
"name": "Qwen3.5-27B-Queen-Derestricted-Lite",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Qwen3.5-27B-RpRMax-v1": {
"id": "Qwen3.5-27B-RpRMax-v1",
"name": "Qwen3.5-27B-RpRMax-v1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Qwen3.5-27B-Vivid-Durian": {
"id": "Qwen3.5-27B-Vivid-Durian",
"name": "Qwen3.5-27B-Vivid-Durian",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Qwen3.5-27B-Writer-Derestricted": {
"id": "Qwen3.5-27B-Writer-Derestricted",
"name": "Qwen3.5-27B-Writer-Derestricted",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Qwen3.5-27B-Writer-Derestricted-Lite": {
"id": "Qwen3.5-27B-Writer-Derestricted-Lite",
"name": "Qwen3.5-27B-Writer-Derestricted-Lite",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Qwen3.5-27B-Writer-V2-Derestricted": {
"id": "Qwen3.5-27B-Writer-V2-Derestricted",
"name": "Qwen3.5-27B-Writer-V2-Derestricted",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Qwen3.5-27B-Writer-V2-Derestricted-Lite": {
"id": "Qwen3.5-27B-Writer-V2-Derestricted-Lite",
"name": "Qwen3.5-27B-Writer-V2-Derestricted-Lite",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"qwen3.5-35b-a3b": {
"id": "qwen3.5-35b-a3b",
"name": "qwen3.5-35b-a3b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen3.5-flash": {
"id": "qwen3.5-flash",
"name": "qwen3.5-flash",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1024000,
"maxTokens": 1020000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen3.5-omni-flash": {
"id": "qwen3.5-omni-flash",
"name": "qwen3.5-omni-flash",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"qwen3.5-omni-plus": {
"id": "qwen3.5-omni-plus",
"name": "qwen3.5-omni-plus",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"qwen3.6-max-preview": {
"id": "qwen3.6-max-preview",
"name": "qwen3.6-max-preview",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536
},
"qwen3.7-max": {
"id": "qwen3.7-max",
"name": "Qwen3.7 Max",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen3.7-plus": {
"id": "qwen3.7-plus",
"name": "Qwen3.7 Plus",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwq-32b": {
"id": "qwq-32b",
"name": "qwq-32b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"QwQ-32B-ArliAI-RpR-v1": {
"id": "QwQ-32B-ArliAI-RpR-v1",
"name": "QwQ-32B-ArliAI-RpR-v1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"raifle/sorcererlm-8x22b": {
"id": "raifle/sorcererlm-8x22b",
"name": "raifle/sorcererlm-8x22b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0": {
"id": "ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0",
"name": "ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"ReadyArt/The-Omega-Abomination-L-70B-v1.0": {
"id": "ReadyArt/The-Omega-Abomination-L-70B-v1.0",
"name": "ReadyArt/The-Omega-Abomination-L-70B-v1.0",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Salesforce/Llama-xLAM-2-70b-fc-r": {
"id": "Salesforce/Llama-xLAM-2-70b-fc-r",
"name": "Salesforce/Llama-xLAM-2-70b-fc-r",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Sao10K/L3-8B-Stheno-v3.2": {
"id": "Sao10K/L3-8B-Stheno-v3.2",
"name": "Sao10K/L3-8B-Stheno-v3.2",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Sao10K/L3.1-70B-Euryale-v2.2": {
"id": "Sao10K/L3.1-70B-Euryale-v2.2",
"name": "Sao10K/L3.1-70B-Euryale-v2.2",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Sao10K/L3.1-70B-Hanami-x1": {
"id": "Sao10K/L3.1-70B-Hanami-x1",
"name": "Sao10K/L3.1-70B-Hanami-x1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Sao10K/L3.3-70B-Euryale-v2.3": {
"id": "Sao10K/L3.3-70B-Euryale-v2.3",
"name": "Sao10K/L3.3-70B-Euryale-v2.3",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"sarvam-105b": {
"id": "sarvam-105b",
"name": "Sarvam 105B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.045,
"output": 0.177,
"cacheRead": 0.028,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 4096,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"sarvam-30b": {
"id": "sarvam-30b",
"name": "Sarvam 30B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.028,
"output": 0.111,
"cacheRead": 0.017,
"cacheWrite": 0
},
"contextWindow": 65536,
"maxTokens": 4096,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"sarvan-medium": {
"id": "sarvan-medium",
"name": "sarvan-medium",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"shisa-ai/shisa-v2-llama3.3-70b": {
"id": "shisa-ai/shisa-v2-llama3.3-70b",
"name": "shisa-ai/shisa-v2-llama3.3-70b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"shisa-ai/shisa-v2.1-llama3.3-70b": {
"id": "shisa-ai/shisa-v2.1-llama3.3-70b",
"name": "shisa-ai/shisa-v2.1-llama3.3-70b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"sonar": {
"id": "sonar",
"name": "sonar",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"sonar-deep-research": {
"id": "sonar-deep-research",
"name": "sonar-deep-research",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"sonar-pro": {
"id": "sonar-pro",
"name": "sonar-pro",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortRouting": {
"off": "sonar-pro",
"minimal": "sonar-reasoning-pro",
"low": "sonar-reasoning-pro",
"medium": "sonar-reasoning-pro",
"high": "sonar-reasoning-pro",
"xhigh": "sonar-reasoning-pro"
}
},
"compat": {
"supportsStore": true,
"supportsDeveloperRole": false,
"supportsMultipleSystemMessages": false,
"supportsReasoningEffort": true,
"supportsReasoningParams": true,
"reasoningEffortMap": {},
"supportsUsageInStreaming": true,
"alwaysSendMaxTokens": false,
"disableReasoningOnForcedToolChoice": false,
"disableReasoningOnToolChoice": false,
"supportsToolChoice": true,
"maxTokensField": "max_completion_tokens",
"requiresToolResultName": false,
"requiresAssistantAfterToolResult": false,
"requiresThinkingAsText": false,
"requiresMistralToolIds": false,
"thinkingFormat": "openai",
"reasoningContentField": "reasoning_content",
"requiresReasoningContentForToolCalls": false,
"allowsSyntheticReasoningContentForToolCalls": true,
"requiresAssistantContentForToolCalls": false,
"isOpenRouterHost": false,
"isVercelGatewayHost": false,
"supportsStrictMode": false,
"toolStrictMode": "mixed"
}
},
"soob3123/amoral-gemma3-27B-v2": {
"id": "soob3123/amoral-gemma3-27B-v2",
"name": "soob3123/amoral-gemma3-27B-v2",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"soob3123/GrayLine-Qwen3-8B": {
"id": "soob3123/GrayLine-Qwen3-8B",
"name": "soob3123/GrayLine-Qwen3-8B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192
},
"soob3123/Veiled-Calla-12B": {
"id": "soob3123/Veiled-Calla-12B",
"name": "soob3123/Veiled-Calla-12B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Steelskull/L3.3-Cu-Mai-R1-70b": {
"id": "Steelskull/L3.3-Cu-Mai-R1-70b",
"name": "Steelskull/L3.3-Cu-Mai-R1-70b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Steelskull/L3.3-Electra-R1-70b": {
"id": "Steelskull/L3.3-Electra-R1-70b",
"name": "Steelskull/L3.3-Electra-R1-70b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Steelskull/L3.3-MS-Evalebis-70b": {
"id": "Steelskull/L3.3-MS-Evalebis-70b",
"name": "Steelskull/L3.3-MS-Evalebis-70b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Steelskull/L3.3-MS-Evayale-70B": {
"id": "Steelskull/L3.3-MS-Evayale-70B",
"name": "Steelskull/L3.3-MS-Evayale-70B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Steelskull/L3.3-MS-Nevoria-70b": {
"id": "Steelskull/L3.3-MS-Nevoria-70b",
"name": "Steelskull/L3.3-MS-Nevoria-70b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Steelskull/L3.3-Nevoria-R1-70b": {
"id": "Steelskull/L3.3-Nevoria-R1-70b",
"name": "Steelskull/L3.3-Nevoria-R1-70b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"step-2-16k-exp": {
"id": "step-2-16k-exp",
"name": "step-2-16k-exp",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"step-2-mini": {
"id": "step-2-mini",
"name": "step-2-mini",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"step-3": {
"id": "step-3",
"name": "step-3",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 65536,
"maxTokens": 64000
},
"step-r1-v-mini": {
"id": "step-r1-v-mini",
"name": "step-r1-v-mini",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"stepfun-ai/step-3.5-flash": {
"id": "stepfun-ai/step-3.5-flash",
"name": "Step 3.5 Flash",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"stepfun-ai/step-3.5-flash-2603": {
"id": "stepfun-ai/step-3.5-flash-2603",
"name": "stepfun-ai/step-3.5-flash-2603",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"stepfun-ai/step-3.6": {
"id": "stepfun-ai/step-3.6",
"name": "stepfun-ai/step-3.6",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"stepfun/step-3.7-flash:thinking": {
"id": "stepfun/step-3.7-flash:thinking",
"name": "Step 3.7 Flash Thinking",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.2,
"output": 1.15,
"cacheRead": 0.04,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"study_gpt-chatgpt-4o-latest": {
"id": "study_gpt-chatgpt-4o-latest",
"name": "study_gpt-chatgpt-4o-latest",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"TEE/deepseek-r1-0528": {
"id": "TEE/deepseek-r1-0528",
"name": "TEE/deepseek-r1-0528",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 32768
},
"TEE/deepseek-v3.1": {
"id": "TEE/deepseek-v3.1",
"name": "TEE/deepseek-v3.1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 8192
},
"TEE/deepseek-v3.2": {
"id": "TEE/deepseek-v3.2",
"name": "TEE/deepseek-v3.2",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 160000,
"maxTokens": 8192
},
"TEE/deepseek-v4-flash": {
"id": "TEE/deepseek-v4-flash",
"name": "TEE/deepseek-v4-flash",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 384000
},
"TEE/deepseek-v4-pro": {
"id": "TEE/deepseek-v4-pro",
"name": "DeepSeek V4 Pro TEE",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.5,
"output": 5.25,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 800000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"TEE/deepseek-v4-pro:thinking": {
"id": "TEE/deepseek-v4-pro:thinking",
"name": "DeepSeek V4 Pro Thinking TEE",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.5,
"output": 5.25,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 800000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"TEE/gemma-3-27b-it": {
"id": "TEE/gemma-3-27b-it",
"name": "TEE/gemma-3-27b-it",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192
},
"TEE/gemma-4-26b-a4b-uncensored": {
"id": "TEE/gemma-4-26b-a4b-uncensored",
"name": "Gemma 4 26B A4B Uncensored TEE",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 0.7,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 65536,
"maxTokens": 65536
},
"TEE/gemma-4-31b-it": {
"id": "TEE/gemma-4-31b-it",
"name": "Gemma 4 31B IT TEE",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.46,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"TEE/gemma4-31b": {
"id": "TEE/gemma4-31b",
"name": "TEE/gemma4-31b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"TEE/glm-4.6": {
"id": "TEE/glm-4.6",
"name": "TEE/glm-4.6",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072
},
"TEE/glm-4.7": {
"id": "TEE/glm-4.7",
"name": "TEE/glm-4.7",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072
},
"TEE/glm-4.7-flash": {
"id": "TEE/glm-4.7-flash",
"name": "TEE/glm-4.7-flash",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 131072
},
"TEE/glm-5": {
"id": "TEE/glm-5",
"name": "TEE/glm-5",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072
},
"TEE/glm-5-1": {
"id": "TEE/glm-5-1",
"name": "TEE/glm-5-1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortRouting": {
"off": "TEE/glm-5-1",
"minimal": "TEE/glm-5-1-thinking",
"low": "TEE/glm-5-1-thinking",
"medium": "TEE/glm-5-1-thinking",
"high": "TEE/glm-5-1-thinking",
"xhigh": "TEE/glm-5-1-thinking"
}
},
"compat": {
"supportsStore": true,
"supportsDeveloperRole": false,
"supportsMultipleSystemMessages": false,
"supportsReasoningEffort": true,
"supportsReasoningParams": true,
"reasoningEffortMap": {},
"supportsUsageInStreaming": true,
"alwaysSendMaxTokens": false,
"disableReasoningOnForcedToolChoice": false,
"disableReasoningOnToolChoice": false,
"supportsToolChoice": true,
"maxTokensField": "max_completion_tokens",
"requiresToolResultName": false,
"requiresAssistantAfterToolResult": false,
"requiresThinkingAsText": false,
"requiresMistralToolIds": false,
"thinkingFormat": "openai",
"reasoningContentField": "reasoning_content",
"requiresReasoningContentForToolCalls": false,
"allowsSyntheticReasoningContentForToolCalls": true,
"requiresAssistantContentForToolCalls": false,
"isOpenRouterHost": false,
"isVercelGatewayHost": false,
"supportsStrictMode": false,
"toolStrictMode": "mixed"
}
},
"TEE/glm-5.1": {
"id": "TEE/glm-5.1",
"name": "TEE/glm-5.1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortRouting": {
"off": "TEE/glm-5.1",
"minimal": "TEE/glm-5.1-thinking",
"low": "TEE/glm-5.1-thinking",
"medium": "TEE/glm-5.1-thinking",
"high": "TEE/glm-5.1-thinking",
"xhigh": "TEE/glm-5.1-thinking"
}
},
"compat": {
"supportsStore": true,
"supportsDeveloperRole": false,
"supportsMultipleSystemMessages": false,
"supportsReasoningEffort": true,
"supportsReasoningParams": true,
"reasoningEffortMap": {},
"supportsUsageInStreaming": true,
"alwaysSendMaxTokens": false,
"disableReasoningOnForcedToolChoice": false,
"disableReasoningOnToolChoice": false,
"supportsToolChoice": true,
"maxTokensField": "max_completion_tokens",
"requiresToolResultName": false,
"requiresAssistantAfterToolResult": false,
"requiresThinkingAsText": false,
"requiresMistralToolIds": false,
"thinkingFormat": "openai",
"reasoningContentField": "reasoning_content",
"requiresReasoningContentForToolCalls": false,
"allowsSyntheticReasoningContentForToolCalls": true,
"requiresAssistantContentForToolCalls": false,
"isOpenRouterHost": false,
"isVercelGatewayHost": false,
"supportsStrictMode": false,
"toolStrictMode": "mixed"
}
},
"TEE/glm-5.2": {
"id": "TEE/glm-5.2",
"name": "TEE/glm-5.2",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072
},
"TEE/gpt-oss-120b": {
"id": "TEE/gpt-oss-120b",
"name": "TEE/gpt-oss-120b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 40960
},
"TEE/gpt-oss-20b": {
"id": "TEE/gpt-oss-20b",
"name": "TEE/gpt-oss-20b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 65536
},
"TEE/kimi-k2-thinking": {
"id": "TEE/kimi-k2-thinking",
"name": "TEE/kimi-k2-thinking",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"TEE/kimi-k2.5": {
"id": "TEE/kimi-k2.5",
"name": "TEE/kimi-k2.5",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortRouting": {
"off": "TEE/kimi-k2.5",
"minimal": "TEE/kimi-k2.5-thinking",
"low": "TEE/kimi-k2.5-thinking",
"medium": "TEE/kimi-k2.5-thinking",
"high": "TEE/kimi-k2.5-thinking",
"xhigh": "TEE/kimi-k2.5-thinking"
}
},
"compat": {
"supportsStore": true,
"supportsDeveloperRole": false,
"supportsMultipleSystemMessages": false,
"supportsReasoningEffort": true,
"supportsReasoningParams": true,
"reasoningEffortMap": {},
"supportsUsageInStreaming": true,
"alwaysSendMaxTokens": true,
"disableReasoningOnForcedToolChoice": true,
"disableReasoningOnToolChoice": false,
"supportsToolChoice": true,
"maxTokensField": "max_completion_tokens",
"requiresToolResultName": false,
"requiresAssistantAfterToolResult": false,
"requiresThinkingAsText": false,
"requiresMistralToolIds": false,
"thinkingFormat": "openai",
"reasoningContentField": "reasoning_content",
"requiresReasoningContentForToolCalls": true,
"allowsSyntheticReasoningContentForToolCalls": true,
"requiresAssistantContentForToolCalls": true,
"isOpenRouterHost": false,
"isVercelGatewayHost": false,
"supportsStrictMode": false,
"toolStrictMode": "mixed"
}
},
"TEE/kimi-k2.6": {
"id": "TEE/kimi-k2.6",
"name": "Kimi K2.6 TEE",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 1.5,
"output": 5.25,
"cacheRead": 0.375,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536
},
"TEE/llama3-3-70b": {
"id": "TEE/llama3-3-70b",
"name": "TEE/llama3-3-70b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"TEE/mimo-v2-flash": {
"id": "TEE/mimo-v2-flash",
"name": "TEE/mimo-v2-flash",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536
},
"TEE/minimax-m2.1": {
"id": "TEE/minimax-m2.1",
"name": "TEE/minimax-m2.1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072
},
"TEE/minimax-m2.5": {
"id": "TEE/minimax-m2.5",
"name": "MiniMax M2.5 TEE",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.2,
"output": 1.38,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 196608,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"TEE/qwen2.5-vl-72b-instruct": {
"id": "TEE/qwen2.5-vl-72b-instruct",
"name": "TEE/qwen2.5-vl-72b-instruct",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"TEE/qwen3-30b-a3b-instruct-2507": {
"id": "TEE/qwen3-30b-a3b-instruct-2507",
"name": "TEE/qwen3-30b-a3b-instruct-2507",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32000
},
"TEE/qwen3-coder": {
"id": "TEE/qwen3-coder",
"name": "TEE/qwen3-coder",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536
},
"TEE/qwen3-coder-next": {
"id": "TEE/qwen3-coder-next",
"name": "TEE/qwen3-coder-next",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536
},
"TEE/qwen3.5-122b-a10b": {
"id": "TEE/qwen3.5-122b-a10b",
"name": "Qwen3.5 122B A10B TEE",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.46,
"output": 3.68,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"TEE/qwen3.5-27b": {
"id": "TEE/qwen3.5-27b",
"name": "TEE/qwen3.5-27b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536
},
"TEE/qwen3.5-397b-a17b": {
"id": "TEE/qwen3.5-397b-a17b",
"name": "TEE/qwen3.5-397b-a17b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536
},
"TEE/qwen3.6-27b": {
"id": "TEE/qwen3.6-27b",
"name": "TEE/qwen3.6-27b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262140
},
"TEE/qwen3.6-35b-a3b": {
"id": "TEE/qwen3.6-35b-a3b",
"name": "TEE/qwen3.6-35b-a3b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 65536
},
"TEE/qwen3.6-35b-a3b-uncensored": {
"id": "TEE/qwen3.6-35b-a3b-uncensored",
"name": "Qwen3.6 35B A3B Uncensored TEE",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 1.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"tencent/Hunyuan-MT-7B": {
"id": "tencent/Hunyuan-MT-7B",
"name": "tencent/Hunyuan-MT-7B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"tencent/hy3-preview": {
"id": "tencent/hy3-preview",
"name": "Hy3 Preview",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"TheDrummer/Anubis-70B-v1": {
"id": "TheDrummer/Anubis-70B-v1",
"name": "TheDrummer/Anubis-70B-v1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"TheDrummer/Anubis-70B-v1.1": {
"id": "TheDrummer/Anubis-70B-v1.1",
"name": "TheDrummer/Anubis-70B-v1.1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"TheDrummer/Cydonia-24B-v2": {
"id": "TheDrummer/Cydonia-24B-v2",
"name": "TheDrummer/Cydonia-24B-v2",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"TheDrummer/Cydonia-24B-v4": {
"id": "TheDrummer/Cydonia-24B-v4",
"name": "TheDrummer/Cydonia-24B-v4",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"TheDrummer/Cydonia-24B-v4.1": {
"id": "TheDrummer/Cydonia-24B-v4.1",
"name": "TheDrummer/Cydonia-24B-v4.1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"TheDrummer/Cydonia-24B-v4.3": {
"id": "TheDrummer/Cydonia-24B-v4.3",
"name": "TheDrummer/Cydonia-24B-v4.3",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"TheDrummer/Magidonia-24B-v4.3": {
"id": "TheDrummer/Magidonia-24B-v4.3",
"name": "TheDrummer/Magidonia-24B-v4.3",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"TheDrummer/Rocinante-12B-v1.1": {
"id": "TheDrummer/Rocinante-12B-v1.1",
"name": "TheDrummer/Rocinante-12B-v1.1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"TheDrummer/Skyfall-31B-v4.2": {
"id": "TheDrummer/Skyfall-31B-v4.2",
"name": "TheDrummer/Skyfall-31B-v4.2",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"thedrummer/skyfall-36b-v2": {
"id": "thedrummer/skyfall-36b-v2",
"name": "thedrummer/skyfall-36b-v2",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"TheDrummer/UnslopNemo-12B-v4.1": {
"id": "TheDrummer/UnslopNemo-12B-v4.1",
"name": "TheDrummer/UnslopNemo-12B-v4.1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"THUDM/GLM-4-32B-0414": {
"id": "THUDM/GLM-4-32B-0414",
"name": "THUDM/GLM-4-32B-0414",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"THUDM/GLM-4-9B-0414": {
"id": "THUDM/GLM-4-9B-0414",
"name": "THUDM/GLM-4-9B-0414",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"THUDM/GLM-Z1-32B-0414": {
"id": "THUDM/GLM-Z1-32B-0414",
"name": "THUDM/GLM-Z1-32B-0414",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"THUDM/GLM-Z1-9B-0414": {
"id": "THUDM/GLM-Z1-9B-0414",
"name": "THUDM/GLM-Z1-9B-0414",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"THUDM/GLM-Z1-Rumination-32B-0414": {
"id": "THUDM/GLM-Z1-Rumination-32B-0414",
"name": "THUDM/GLM-Z1-Rumination-32B-0414",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"tngtech/DeepSeek-TNG-R1T2-Chimera": {
"id": "tngtech/DeepSeek-TNG-R1T2-Chimera",
"name": "tngtech/DeepSeek-TNG-R1T2-Chimera",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"tngtech/tng-r1t-chimera": {
"id": "tngtech/tng-r1t-chimera",
"name": "R1T Chimera",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.25,
"output": 0.85,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"Tongyi-Zhiwen/QwenLong-L1-32B": {
"id": "Tongyi-Zhiwen/QwenLong-L1-32B",
"name": "Tongyi-Zhiwen/QwenLong-L1-32B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"Unbabel/M-Prometheus-14B": {
"id": "Unbabel/M-Prometheus-14B",
"name": "Unbabel/M-Prometheus-14B",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"undi95/remm-slerp-l2-13b": {
"id": "undi95/remm-slerp-l2-13b",
"name": "undi95/remm-slerp-l2-13b",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"universal-summarizer": {
"id": "universal-summarizer",
"name": "universal-summarizer",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"unsloth/gemma-3-12b-it": {
"id": "unsloth/gemma-3-12b-it",
"name": "unsloth/gemma-3-12b-it",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384
},
"unsloth/gemma-3-1b-it": {
"id": "unsloth/gemma-3-1b-it",
"name": "unsloth/gemma-3-1b-it",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"unsloth/gemma-3-27b-it": {
"id": "unsloth/gemma-3-27b-it",
"name": "unsloth/gemma-3-27b-it",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192
},
"unsloth/gemma-3-4b-it": {
"id": "unsloth/gemma-3-4b-it",
"name": "unsloth/gemma-3-4b-it",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"upstage/solar-pro-3": {
"id": "upstage/solar-pro-3",
"name": "Solar Pro 3",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"v0-1.0-md": {
"id": "v0-1.0-md",
"name": "v0-1.0-md",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"v0-1.5-lg": {
"id": "v0-1.5-lg",
"name": "v0-1.5-lg",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"v0-1.5-md": {
"id": "v0-1.5-md",
"name": "v0-1.5-md",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"venice-uncensored": {
"id": "venice-uncensored",
"name": "Venice Uncensored 1.1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32000,
"maxTokens": 8192,
"compat": {
"supportsUsageInStreaming": false
}
},
"venice-uncensored:web": {
"id": "venice-uncensored:web",
"name": "venice-uncensored:web",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"VongolaChouko/Starcannon-Unleashed-12B-v1.0": {
"id": "VongolaChouko/Starcannon-Unleashed-12B-v1.0",
"name": "VongolaChouko/Starcannon-Unleashed-12B-v1.0",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"x-ai/grok-4-07-09": {
"id": "x-ai/grok-4-07-09",
"name": "x-ai/grok-4-07-09",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"x-ai/grok-4-fast": {
"id": "x-ai/grok-4-fast",
"name": "Grok 4 Fast",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.19999999999999998,
"output": 0.5,
"cacheRead": 0.049999999999999996,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"x-ai/grok-4.1-fast": {
"id": "x-ai/grok-4.1-fast",
"name": "Grok 4.1 Fast",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.19999999999999998,
"output": 0.5,
"cacheRead": 0.049999999999999996,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortRouting": {
"off": "x-ai/grok-4.1-fast",
"minimal": "x-ai/grok-4.1-fast-reasoning",
"low": "x-ai/grok-4.1-fast-reasoning",
"medium": "x-ai/grok-4.1-fast-reasoning",
"high": "x-ai/grok-4.1-fast-reasoning",
"xhigh": "x-ai/grok-4.1-fast-reasoning"
}
},
"compat": {
"supportsStore": true,
"supportsDeveloperRole": false,
"supportsMultipleSystemMessages": false,
"supportsReasoningEffort": true,
"supportsReasoningParams": true,
"reasoningEffortMap": {},
"supportsUsageInStreaming": true,
"alwaysSendMaxTokens": false,
"disableReasoningOnForcedToolChoice": false,
"disableReasoningOnToolChoice": false,
"supportsToolChoice": true,
"maxTokensField": "max_completion_tokens",
"requiresToolResultName": false,
"requiresAssistantAfterToolResult": false,
"requiresThinkingAsText": false,
"requiresMistralToolIds": false,
"thinkingFormat": "openai",
"reasoningContentField": "reasoning_content",
"requiresReasoningContentForToolCalls": false,
"allowsSyntheticReasoningContentForToolCalls": true,
"requiresAssistantContentForToolCalls": false,
"isOpenRouterHost": false,
"isVercelGatewayHost": false,
"supportsStrictMode": false,
"toolStrictMode": "mixed"
}
},
"x-ai/grok-4.20": {
"id": "x-ai/grok-4.20",
"name": "Grok 4.20",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"x-ai/grok-4.20-beta-non-reasoning": {
"id": "x-ai/grok-4.20-beta-non-reasoning",
"name": "x-ai/grok-4.20-beta-non-reasoning",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"x-ai/grok-4.20-beta-reasoning": {
"id": "x-ai/grok-4.20-beta-reasoning",
"name": "x-ai/grok-4.20-beta-reasoning",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"x-ai/grok-4.20-multi-agent": {
"id": "x-ai/grok-4.20-multi-agent",
"name": "Grok 4.20 Multi-Agent",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"x-ai/grok-4.20-multi-agent-beta": {
"id": "x-ai/grok-4.20-multi-agent-beta",
"name": "x-ai/grok-4.20-multi-agent-beta",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 2000000
},
"x-ai/grok-4.3": {
"id": "x-ai/grok-4.3",
"name": "Grok 4.3",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 2.5,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 1000000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"x-ai/grok-build-0.1": {
"id": "x-ai/grok-build-0.1",
"name": "Grok Build 0.1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1,
"output": 2,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"x-ai/grok-code-fast-1": {
"id": "x-ai/grok-code-fast-1",
"name": "Grok Code Fast 1",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.19999999999999998,
"output": 1.5,
"cacheRead": 0.02,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"x-ai/grok-latest": {
"id": "x-ai/grok-latest",
"name": "Grok Latest",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 2.5,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 1000000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"xiaomi/mimo-v2-flash": {
"id": "xiaomi/mimo-v2-flash",
"name": "MiMo-V2-Flash",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.09,
"output": 0.29,
"cacheRead": 0.045,
"cacheWrite": 0
},
"contextWindow": 262000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortRouting": {
"off": "xiaomi/mimo-v2-flash",
"minimal": "xiaomi/mimo-v2-flash-thinking",
"low": "xiaomi/mimo-v2-flash-thinking",
"medium": "xiaomi/mimo-v2-flash-thinking",
"high": "xiaomi/mimo-v2-flash-thinking",
"xhigh": "xiaomi/mimo-v2-flash-thinking"
}
},
"compat": {
"supportsStore": true,
"supportsDeveloperRole": false,
"supportsMultipleSystemMessages": false,
"supportsReasoningEffort": true,
"supportsReasoningParams": true,
"reasoningEffortMap": {},
"supportsUsageInStreaming": true,
"alwaysSendMaxTokens": false,
"disableReasoningOnForcedToolChoice": false,
"disableReasoningOnToolChoice": false,
"supportsToolChoice": true,
"maxTokensField": "max_completion_tokens",
"requiresToolResultName": false,
"requiresAssistantAfterToolResult": false,
"requiresThinkingAsText": false,
"requiresMistralToolIds": false,
"thinkingFormat": "openai",
"reasoningContentField": "reasoning_content",
"requiresReasoningContentForToolCalls": false,
"allowsSyntheticReasoningContentForToolCalls": true,
"requiresAssistantContentForToolCalls": false,
"isOpenRouterHost": false,
"isVercelGatewayHost": false,
"supportsStrictMode": false,
"toolStrictMode": "mixed"
}
},
"xiaomi/mimo-v2-flash-original": {
"id": "xiaomi/mimo-v2-flash-original",
"name": "xiaomi/mimo-v2-flash-original",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortRouting": {
"off": "xiaomi/mimo-v2-flash-original",
"minimal": "xiaomi/mimo-v2-flash-thinking-original",
"low": "xiaomi/mimo-v2-flash-thinking-original",
"medium": "xiaomi/mimo-v2-flash-thinking-original",
"high": "xiaomi/mimo-v2-flash-thinking-original",
"xhigh": "xiaomi/mimo-v2-flash-thinking-original"
}
},
"compat": {
"supportsStore": true,
"supportsDeveloperRole": false,
"supportsMultipleSystemMessages": false,
"supportsReasoningEffort": true,
"supportsReasoningParams": true,
"reasoningEffortMap": {},
"supportsUsageInStreaming": true,
"alwaysSendMaxTokens": false,
"disableReasoningOnForcedToolChoice": false,
"disableReasoningOnToolChoice": false,
"supportsToolChoice": true,
"maxTokensField": "max_completion_tokens",
"requiresToolResultName": false,
"requiresAssistantAfterToolResult": false,
"requiresThinkingAsText": false,
"requiresMistralToolIds": false,
"thinkingFormat": "openai",
"reasoningContentField": "reasoning_content",
"requiresReasoningContentForToolCalls": false,
"allowsSyntheticReasoningContentForToolCalls": true,
"requiresAssistantContentForToolCalls": false,
"isOpenRouterHost": false,
"isVercelGatewayHost": false,
"supportsStrictMode": false,
"toolStrictMode": "mixed"
}
},
"xiaomi/mimo-v2-omni": {
"id": "xiaomi/mimo-v2-omni",
"name": "MiMo V2 Omni",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.4,
"output": 2,
"cacheRead": 0.08,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"xiaomi/mimo-v2-pro": {
"id": "xiaomi/mimo-v2-pro",
"name": "MiMo V2 Pro",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 3,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"xiaomi/mimo-v2.5": {
"id": "xiaomi/mimo-v2.5",
"name": "MiMo V2.5",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.14,
"output": 0.28,
"cacheRead": 0.0028,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"xiaomi/mimo-v2.5-pro": {
"id": "xiaomi/mimo-v2.5-pro",
"name": "MiMo V2.5 Pro",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.435,
"output": 0.87,
"cacheRead": 0.0036,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"xiaomi/mimo-v2.5-pro-ultraspeed": {
"id": "xiaomi/mimo-v2.5-pro-ultraspeed",
"name": "xiaomi/mimo-v2.5-pro-ultraspeed",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072
},
"yi-large": {
"id": "yi-large",
"name": "yi-large",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"yi-lightning": {
"id": "yi-lightning",
"name": "yi-lightning",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"yi-medium-200k": {
"id": "yi-medium-200k",
"name": "yi-medium-200k",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"z-ai/glm-4.5v": {
"id": "z-ai/glm-4.5v",
"name": "GLM 4.5V",
"api": "openai-completions",
"baseUrl": "https://nano-gpt.com/api/v1",
"provider": "nanogpt",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.6,
"output": 1.7999999999999998,
"cacheRead": 0.11,
"cacheWrite": 0
},
"contextWindow": 64000,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"z-ai/glm-4.6": {
"id": "z-ai/glm-4.6",
"name": "GLM 4.6",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.4,
"output": 1.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 65535,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"z-ai/glm-4.6:thinking": {
"id": "z-ai/glm-4.6:thinking",
"name": "GLM 4.6 Thinking",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.4,
"output": 1.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 65535,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"z-ai/glm-5-turbo": {
"id": "z-ai/glm-5-turbo",
"name": "GLM 5 Turbo",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 1.2,
"output": 4,
"cacheRead": 0.24,
"cacheWrite": 0
},
"contextWindow": 202800,
"maxTokens": 131072
},
"z-ai/glm-5v-turbo": {
"id": "z-ai/glm-5v-turbo",
"name": "GLM 5V Turbo",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 1.2,
"output": 4,
"cacheRead": 0.24,
"cacheWrite": 0
},
"contextWindow": 202800,
"maxTokens": 131100
},
"z-ai/glm-5v-turbo:thinking": {
"id": "z-ai/glm-5v-turbo:thinking",
"name": "GLM 5V Turbo Thinking",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.2,
"output": 4,
"cacheRead": 0.24,
"cacheWrite": 0
},
"contextWindow": 202800,
"maxTokens": 131100,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai-org/glm-4.5": {
"id": "zai-org/glm-4.5",
"name": "zai-org/glm-4.5",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 98304
},
"zai-org/GLM-4.5-Air": {
"id": "zai-org/GLM-4.5-Air",
"name": "GLM 4.5 Air",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.12,
"output": 0.8,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 98304
},
"zai-org/GLM-4.5-Air:thinking": {
"id": "zai-org/GLM-4.5-Air:thinking",
"name": "GLM 4.5 Air (Thinking)",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.12,
"output": 0.8,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 98304,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai-org/glm-4.6-original": {
"id": "zai-org/glm-4.6-original",
"name": "zai-org/glm-4.6-original",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072
},
"zai-org/GLM-4.6-turbo": {
"id": "zai-org/GLM-4.6-turbo",
"name": "zai-org/GLM-4.6-turbo",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai-org/glm-4.6v": {
"id": "zai-org/glm-4.6v",
"name": "zai-org/glm-4.6v",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 32768
},
"zai-org/glm-4.6v-flash-original": {
"id": "zai-org/glm-4.6v-flash-original",
"name": "zai-org/glm-4.6v-flash-original",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000
},
"zai-org/glm-4.6v-original": {
"id": "zai-org/glm-4.6v-original",
"name": "zai-org/glm-4.6v-original",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 32768
},
"zai-org/glm-4.7": {
"id": "zai-org/glm-4.7",
"name": "GLM 4.7",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.8,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai-org/glm-4.7-flash": {
"id": "zai-org/glm-4.7-flash",
"name": "GLM 4.7 Flash",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.07,
"output": 0.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai-org/glm-4.7-flash-original": {
"id": "zai-org/glm-4.7-flash-original",
"name": "GLM 4.7 Flash Original",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.07,
"output": 0.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai-org/glm-4.7-original": {
"id": "zai-org/glm-4.7-original",
"name": "GLM 4.7 Original",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.2,
"cacheRead": 0.11,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 65535,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai-org/glm-4.7-original:thinking": {
"id": "zai-org/glm-4.7-original:thinking",
"name": "GLM 4.7 Original Thinking",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.2,
"cacheRead": 0.11,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 65535,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai-org/glm-4.7:thinking": {
"id": "zai-org/glm-4.7:thinking",
"name": "GLM 4.7 Thinking",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.2,
"output": 0.8,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 65535,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai-org/glm-5": {
"id": "zai-org/glm-5",
"name": "GLM 5",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 2.55,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai-org/GLM-5-NVFP4-TEE": {
"id": "zai-org/GLM-5-NVFP4-TEE",
"name": "zai-org/GLM-5-NVFP4-TEE",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"zai-org/glm-5-original": {
"id": "zai-org/glm-5-original",
"name": "GLM 5 Original",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 3.2,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai-org/glm-5-original:thinking": {
"id": "zai-org/glm-5-original:thinking",
"name": "GLM 5 Original Thinking",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 3.2,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai-org/glm-5:thinking": {
"id": "zai-org/glm-5:thinking",
"name": "GLM 5 Thinking",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 2.55,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai-org/glm-5.1": {
"id": "zai-org/glm-5.1",
"name": "GLM 5.1",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 2.55,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai-org/glm-5.1:thinking": {
"id": "zai-org/glm-5.1:thinking",
"name": "GLM 5.1 Thinking",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 2.55,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai-org/glm-5.2": {
"id": "zai-org/glm-5.2",
"name": "zai-org/glm-5.2",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai-org/glm-latest": {
"id": "zai-org/glm-latest",
"name": "GLM Latest",
"api": "openai-completions",
"provider": "nanogpt",
"baseUrl": "https://nano-gpt.com/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.75,
"output": 2.6,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
}
},
"nvidia": {
"01-ai/yi-large": {
"id": "01-ai/yi-large",
"name": "01-ai/yi-large",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"abacusai/dracarys-llama-3_1-70b-instruct": {
"id": "abacusai/dracarys-llama-3_1-70b-instruct",
"name": "dracarys-llama-3.1-70b-instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"abacusai/dracarys-llama-3.1-70b-instruct": {
"id": "abacusai/dracarys-llama-3.1-70b-instruct",
"name": "abacusai/dracarys-llama-3.1-70b-instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384
},
"adept/fuyu-8b": {
"id": "adept/fuyu-8b",
"name": "adept/fuyu-8b",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"ai21labs/jamba-1.5-large-instruct": {
"id": "ai21labs/jamba-1.5-large-instruct",
"name": "ai21labs/jamba-1.5-large-instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"aisingapore/sea-lion-7b-instruct": {
"id": "aisingapore/sea-lion-7b-instruct",
"name": "aisingapore/sea-lion-7b-instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"baai/bge-m3": {
"id": "baai/bge-m3",
"name": "baai/bge-m3",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"bigcode/starcoder2-15b": {
"id": "bigcode/starcoder2-15b",
"name": "bigcode/starcoder2-15b",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"bytedance/seed-oss-36b-instruct": {
"id": "bytedance/seed-oss-36b-instruct",
"name": "ByteDance-Seed/Seed-OSS-36B-Instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262000,
"maxTokens": 262000
},
"databricks/dbrx-instruct": {
"id": "databricks/dbrx-instruct",
"name": "databricks/dbrx-instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"deepseek-ai/deepseek-coder-6.7b-instruct": {
"id": "deepseek-ai/deepseek-coder-6.7b-instruct",
"name": "Deepseek Coder 6.7b Instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"deepseek-ai/deepseek-r1-0528": {
"id": "deepseek-ai/deepseek-r1-0528",
"name": "Deepseek R1 0528",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek-ai/deepseek-v3.1": {
"id": "deepseek-ai/deepseek-v3.1",
"name": "DeepSeek V3.1",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek-ai/deepseek-v3.1-terminus": {
"id": "deepseek-ai/deepseek-v3.1-terminus",
"name": "DeepSeek V3.1 Terminus",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek-ai/deepseek-v3.2": {
"id": "deepseek-ai/deepseek-v3.2",
"name": "DeepSeek V3.2",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek-ai/deepseek-v4-flash": {
"id": "deepseek-ai/deepseek-v4-flash",
"name": "DeepSeek V4 Flash",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.14,
"output": 0.28,
"cacheRead": 0.0028,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 393216,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek-ai/deepseek-v4-pro": {
"id": "deepseek-ai/deepseek-v4-pro",
"name": "DeepSeek V4 Pro",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.435,
"output": 0.87,
"cacheRead": 0.003625,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 393216,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"google/codegemma-1.1-7b": {
"id": "google/codegemma-1.1-7b",
"name": "google/codegemma-1.1-7b",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"google/codegemma-7b": {
"id": "google/codegemma-7b",
"name": "google/codegemma-7b",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"google/deplot": {
"id": "google/deplot",
"name": "google/deplot",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"google/gemma-2-27b-it": {
"id": "google/gemma-2-27b-it",
"name": "Gemma 2 27b It",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"google/gemma-2-2b-it": {
"id": "google/gemma-2-2b-it",
"name": "Gemma 2 2b It",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"google/gemma-2b": {
"id": "google/gemma-2b",
"name": "google/gemma-2b",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"google/gemma-3-12b-it": {
"id": "google/gemma-3-12b-it",
"name": "Gemma 3 12b It",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"google/gemma-3-1b-it": {
"id": "google/gemma-3-1b-it",
"name": "Gemma 3 1b It",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"google/gemma-3-27b-it": {
"id": "google/gemma-3-27b-it",
"name": "Gemma 3 27B",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192
},
"google/gemma-3-4b-it": {
"id": "google/gemma-3-4b-it",
"name": "google/gemma-3-4b-it",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"google/gemma-3n-e2b-it": {
"id": "google/gemma-3n-e2b-it",
"name": "Gemma 3n E2b It",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"google/gemma-3n-e4b-it": {
"id": "google/gemma-3n-e4b-it",
"name": "Gemma 3n E4b It",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"google/gemma-4-31b-it": {
"id": "google/gemma-4-31b-it",
"name": "Gemma-4-31B-IT",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"google/recurrentgemma-2b": {
"id": "google/recurrentgemma-2b",
"name": "google/recurrentgemma-2b",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"ibm/granite-3.0-3b-a800m-instruct": {
"id": "ibm/granite-3.0-3b-a800m-instruct",
"name": "ibm/granite-3.0-3b-a800m-instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"ibm/granite-3.0-8b-instruct": {
"id": "ibm/granite-3.0-8b-instruct",
"name": "ibm/granite-3.0-8b-instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"ibm/granite-34b-code-instruct": {
"id": "ibm/granite-34b-code-instruct",
"name": "ibm/granite-34b-code-instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"ibm/granite-8b-code-instruct": {
"id": "ibm/granite-8b-code-instruct",
"name": "ibm/granite-8b-code-instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"meta/codellama-70b": {
"id": "meta/codellama-70b",
"name": "meta/codellama-70b",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"meta/llama-3.1-405b-instruct": {
"id": "meta/llama-3.1-405b-instruct",
"name": "Llama 3.1 405b Instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"meta/llama-3.1-70b-instruct": {
"id": "meta/llama-3.1-70b-instruct",
"name": "Llama 3.1 70b Instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"meta/llama-3.1-8b-instruct": {
"id": "meta/llama-3.1-8b-instruct",
"name": "Llama 3.1 8B Instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 16000,
"maxTokens": 4096
},
"meta/llama-3.2-11b-vision-instruct": {
"id": "meta/llama-3.2-11b-vision-instruct",
"name": "Llama 3.2 11b Vision Instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"meta/llama-3.2-1b-instruct": {
"id": "meta/llama-3.2-1b-instruct",
"name": "Llama 3.2 1b Instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"meta/llama-3.2-3b-instruct": {
"id": "meta/llama-3.2-3b-instruct",
"name": "meta/llama-3.2-3b-instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"meta/llama-3.2-90b-vision-instruct": {
"id": "meta/llama-3.2-90b-vision-instruct",
"name": "Llama-3.2-90B-Vision-Instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"meta/llama-3.3-70b-instruct": {
"id": "meta/llama-3.3-70b-instruct",
"name": "Llama 3.3 70b Instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"meta/llama-4-maverick-17b-128e-instruct": {
"id": "meta/llama-4-maverick-17b-128e-instruct",
"name": "Llama 4 Maverick 17b 128e Instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"meta/llama-4-scout-17b-16e-instruct": {
"id": "meta/llama-4-scout-17b-16e-instruct",
"name": "Llama 4 Scout 17b 16e Instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"meta/llama-guard-4-12b": {
"id": "meta/llama-guard-4-12b",
"name": "meta/llama-guard-4-12b",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"meta/llama2-70b": {
"id": "meta/llama2-70b",
"name": "meta/llama2-70b",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"meta/llama3-70b-instruct": {
"id": "meta/llama3-70b-instruct",
"name": "Llama3 70b Instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"meta/llama3-8b-instruct": {
"id": "meta/llama3-8b-instruct",
"name": "Llama3 8b Instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"microsoft/kosmos-2": {
"id": "microsoft/kosmos-2",
"name": "microsoft/kosmos-2",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"microsoft/phi-3-medium-128k-instruct": {
"id": "microsoft/phi-3-medium-128k-instruct",
"name": "Phi 3 Medium 128k Instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"microsoft/phi-3-medium-4k-instruct": {
"id": "microsoft/phi-3-medium-4k-instruct",
"name": "Phi 3 Medium 4k Instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 4000,
"maxTokens": 4096
},
"microsoft/phi-3-small-128k-instruct": {
"id": "microsoft/phi-3-small-128k-instruct",
"name": "Phi 3 Small 128k Instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"microsoft/phi-3-small-8k-instruct": {
"id": "microsoft/phi-3-small-8k-instruct",
"name": "Phi 3 Small 8k Instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 8000,
"maxTokens": 4096
},
"microsoft/phi-3-vision-128k-instruct": {
"id": "microsoft/phi-3-vision-128k-instruct",
"name": "Phi 3 Vision 128k Instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"microsoft/phi-3.5-moe-instruct": {
"id": "microsoft/phi-3.5-moe-instruct",
"name": "Phi 3.5 Moe Instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"microsoft/phi-3.5-vision-instruct": {
"id": "microsoft/phi-3.5-vision-instruct",
"name": "Phi 3.5 Vision Instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"microsoft/phi-4-mini-instruct": {
"id": "microsoft/phi-4-mini-instruct",
"name": "Phi-4-Mini",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192
},
"microsoft/phi-4-multimodal-instruct": {
"id": "microsoft/phi-4-multimodal-instruct",
"name": "microsoft/phi-4-multimodal-instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"minimaxai/minimax-m2": {
"id": "minimaxai/minimax-m2",
"name": "MiniMax-M2",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimaxai/minimax-m2.1": {
"id": "minimaxai/minimax-m2.1",
"name": "MiniMax-M2.1",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimaxai/minimax-m2.5": {
"id": "minimaxai/minimax-m2.5",
"name": "MiniMax-M2.5",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimaxai/minimax-m2.7": {
"id": "minimaxai/minimax-m2.7",
"name": "MiniMax-M2.7",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"mistralai/codestral-22b-instruct-v0.1": {
"id": "mistralai/codestral-22b-instruct-v0.1",
"name": "Codestral 22b Instruct V0.1",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"mistralai/devstral-2-123b-instruct-2512": {
"id": "mistralai/devstral-2-123b-instruct-2512",
"name": "Devstral-2-123B-Instruct-2512",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"mistralai/ministral-14b-instruct-2512": {
"id": "mistralai/ministral-14b-instruct-2512",
"name": "Ministral 3 14B Instruct 2512",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"mistralai/mistral-7b-instruct-v0.3": {
"id": "mistralai/mistral-7b-instruct-v0.3",
"name": "mistralai/mistral-7b-instruct-v0.3",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"mistralai/mistral-7b-instruct-v03": {
"id": "mistralai/mistral-7b-instruct-v03",
"name": "Mistral-7B-Instruct-v0.3",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 65536,
"maxTokens": 65536
},
"mistralai/mistral-large": {
"id": "mistralai/mistral-large",
"name": "Mistral Large",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 25600
},
"mistralai/mistral-large-2-instruct": {
"id": "mistralai/mistral-large-2-instruct",
"name": "Mistral Large 2 Instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"mistralai/mistral-large-3-675b-instruct-2512": {
"id": "mistralai/mistral-large-3-675b-instruct-2512",
"name": "Mistral Large 3 675B Instruct 2512",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"mistralai/mistral-medium-3.5-128b": {
"id": "mistralai/mistral-medium-3.5-128b",
"name": "Mistral Medium 3.5 128B",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"mistralai/mistral-nemotron": {
"id": "mistralai/mistral-nemotron",
"name": "mistral-nemotron",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"mistralai/mistral-small-3.1-24b-instruct-2503": {
"id": "mistralai/mistral-small-3.1-24b-instruct-2503",
"name": "Mistral Small 3.1 24b Instruct 2503",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"mistralai/mistral-small-4-119b-2603": {
"id": "mistralai/mistral-small-4-119b-2603",
"name": "mistral-small-4-119b-2603",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"mistralai/mixtral-8x22b-instruct": {
"id": "mistralai/mixtral-8x22b-instruct",
"name": "Mixtral 8x22B Instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 65536,
"maxTokens": 13108
},
"mistralai/mixtral-8x22b-v0.1": {
"id": "mistralai/mixtral-8x22b-v0.1",
"name": "mistralai/mixtral-8x22b-v0.1",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"mistralai/mixtral-8x7b-instruct": {
"id": "mistralai/mixtral-8x7b-instruct",
"name": "Mixtral 8x7B Instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32768,
"maxTokens": 16384
},
"mistralai/mixtral-8x7b-instruct-v0.1": {
"id": "mistralai/mixtral-8x7b-instruct-v0.1",
"name": "mistralai/mixtral-8x7b-instruct-v0.1",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"moonshotai/kimi-k2-instruct": {
"id": "moonshotai/kimi-k2-instruct",
"name": "Kimi K2 Instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"moonshotai/kimi-k2-instruct-0905": {
"id": "moonshotai/kimi-k2-instruct-0905",
"name": "Kimi K2 0905",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"moonshotai/kimi-k2-thinking": {
"id": "moonshotai/kimi-k2-thinking",
"name": "Kimi K2 Thinking",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"moonshotai/kimi-k2.5": {
"id": "moonshotai/kimi-k2.5",
"name": "Kimi K2.5",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"moonshotai/kimi-k2.6": {
"id": "moonshotai/kimi-k2.6",
"name": "Kimi K2.6",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nv-mistralai/mistral-nemo-12b-instruct": {
"id": "nv-mistralai/mistral-nemo-12b-instruct",
"name": "nv-mistralai/mistral-nemo-12b-instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/ai-synthetic-video-detector": {
"id": "nvidia/ai-synthetic-video-detector",
"name": "nvidia/ai-synthetic-video-detector",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/cosmos-reason2-8b": {
"id": "nvidia/cosmos-reason2-8b",
"name": "nvidia/cosmos-reason2-8b",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/embed-qa-4": {
"id": "nvidia/embed-qa-4",
"name": "nvidia/embed-qa-4",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/gliner-pii": {
"id": "nvidia/gliner-pii",
"name": "nvidia/gliner-pii",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/ising-calibration-1-35b-a3b": {
"id": "nvidia/ising-calibration-1-35b-a3b",
"name": "nvidia/ising-calibration-1-35b-a3b",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/llama-3_3-nemotron-super-49b-v1": {
"id": "nvidia/llama-3_3-nemotron-super-49b-v1",
"name": "Llama 3.3 Nemotron Super 49B v1",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nvidia/llama-3_3-nemotron-super-49b-v1_5": {
"id": "nvidia/llama-3_3-nemotron-super-49b-v1_5",
"name": "Llama 3.3 Nemotron Super 49B v1.5",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nvidia/llama-3.1-nemoguard-8b-content-safety": {
"id": "nvidia/llama-3.1-nemoguard-8b-content-safety",
"name": "nvidia/llama-3.1-nemoguard-8b-content-safety",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/llama-3.1-nemoguard-8b-topic-control": {
"id": "nvidia/llama-3.1-nemoguard-8b-topic-control",
"name": "nvidia/llama-3.1-nemoguard-8b-topic-control",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/llama-3.1-nemotron-51b-instruct": {
"id": "nvidia/llama-3.1-nemotron-51b-instruct",
"name": "Llama 3.1 Nemotron 51b Instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"nvidia/llama-3.1-nemotron-70b-instruct": {
"id": "nvidia/llama-3.1-nemotron-70b-instruct",
"name": "Llama 3.1 Nemotron 70b Instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"nvidia/llama-3.1-nemotron-nano-8b-v1": {
"id": "nvidia/llama-3.1-nemotron-nano-8b-v1",
"name": "nvidia/llama-3.1-nemotron-nano-8b-v1",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/llama-3.1-nemotron-nano-vl-8b-v1": {
"id": "nvidia/llama-3.1-nemotron-nano-vl-8b-v1",
"name": "nvidia/llama-3.1-nemotron-nano-vl-8b-v1",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/llama-3.1-nemotron-safety-guard-8b-v3": {
"id": "nvidia/llama-3.1-nemotron-safety-guard-8b-v3",
"name": "nvidia/llama-3.1-nemotron-safety-guard-8b-v3",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/llama-3.1-nemotron-ultra-253b-v1": {
"id": "nvidia/llama-3.1-nemotron-ultra-253b-v1",
"name": "Llama-3.1-Nemotron-Ultra-253B-v1",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nvidia/llama-3.2-nemoretriever-1b-vlm-embed-v1": {
"id": "nvidia/llama-3.2-nemoretriever-1b-vlm-embed-v1",
"name": "nvidia/llama-3.2-nemoretriever-1b-vlm-embed-v1",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/llama-3.2-nv-embedqa-1b-v1": {
"id": "nvidia/llama-3.2-nv-embedqa-1b-v1",
"name": "nvidia/llama-3.2-nv-embedqa-1b-v1",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/llama-3.3-nemotron-super-49b-v1": {
"id": "nvidia/llama-3.3-nemotron-super-49b-v1",
"name": "nvidia/llama-3.3-nemotron-super-49b-v1",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/llama-3.3-nemotron-super-49b-v1.5": {
"id": "nvidia/llama-3.3-nemotron-super-49b-v1.5",
"name": "Llama 3.3 Nemotron Super 49B V1.5",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nvidia/llama-nemotron-embed-1b-v2": {
"id": "nvidia/llama-nemotron-embed-1b-v2",
"name": "nvidia/llama-nemotron-embed-1b-v2",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/llama-nemotron-embed-vl-1b-v2": {
"id": "nvidia/llama-nemotron-embed-vl-1b-v2",
"name": "nvidia/llama-nemotron-embed-vl-1b-v2",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/llama3-chatqa-1.5-70b": {
"id": "nvidia/llama3-chatqa-1.5-70b",
"name": "Llama3 Chatqa 1.5 70b",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"nvidia/mistral-nemo-minitron-8b-8k-instruct": {
"id": "nvidia/mistral-nemo-minitron-8b-8k-instruct",
"name": "nvidia/mistral-nemo-minitron-8b-8k-instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 4096
},
"nvidia/nemoretriever-parse": {
"id": "nvidia/nemoretriever-parse",
"name": "nvidia/nemoretriever-parse",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/nemotron-3-content-safety": {
"id": "nvidia/nemotron-3-content-safety",
"name": "nvidia/nemotron-3-content-safety",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/nemotron-3-nano-30b-a3b": {
"id": "nvidia/nemotron-3-nano-30b-a3b",
"name": "nemotron-3-nano-30b-a3b",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning": {
"id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
"name": "Nemotron 3 Nano Omni",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"nvidia/nemotron-3-super-120b-a12b": {
"id": "nvidia/nemotron-3-super-120b-a12b",
"name": "Nemotron 3 Super",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.2,
"output": 0.8,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nvidia/nemotron-3-ultra-550b-a55b": {
"id": "nvidia/nemotron-3-ultra-550b-a55b",
"name": "Nemotron 3 Ultra 550B A55B",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.5,
"output": 2.5,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nvidia/nemotron-3.5-content-safety": {
"id": "nvidia/nemotron-3.5-content-safety",
"name": "nvidia/nemotron-3.5-content-safety",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/nemotron-4-340b-instruct": {
"id": "nvidia/nemotron-4-340b-instruct",
"name": "Nemotron 4 340b Instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"nvidia/nemotron-4-340b-reward": {
"id": "nvidia/nemotron-4-340b-reward",
"name": "nvidia/nemotron-4-340b-reward",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/nemotron-content-safety-reasoning-4b": {
"id": "nvidia/nemotron-content-safety-reasoning-4b",
"name": "nvidia/nemotron-content-safety-reasoning-4b",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/nemotron-mini-4b-instruct": {
"id": "nvidia/nemotron-mini-4b-instruct",
"name": "nemotron-mini-4b-instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"nvidia/nemotron-nano-12b-v2-vl": {
"id": "nvidia/nemotron-nano-12b-v2-vl",
"name": "nvidia/nemotron-nano-12b-v2-vl",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/nemotron-nano-3-30b-a3b": {
"id": "nvidia/nemotron-nano-3-30b-a3b",
"name": "nvidia/nemotron-nano-3-30b-a3b",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/nemotron-parse": {
"id": "nvidia/nemotron-parse",
"name": "nvidia/nemotron-parse",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/nemotron-voicechat": {
"id": "nvidia/nemotron-voicechat",
"name": "nemotron-voicechat",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"nvidia/neva-22b": {
"id": "nvidia/neva-22b",
"name": "nvidia/neva-22b",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/nv-embed-v1": {
"id": "nvidia/nv-embed-v1",
"name": "nvidia/nv-embed-v1",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/nv-embedcode-7b-v1": {
"id": "nvidia/nv-embedcode-7b-v1",
"name": "nvidia/nv-embedcode-7b-v1",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/nv-embedqa-e5-v5": {
"id": "nvidia/nv-embedqa-e5-v5",
"name": "nvidia/nv-embedqa-e5-v5",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/nv-embedqa-mistral-7b-v2": {
"id": "nvidia/nv-embedqa-mistral-7b-v2",
"name": "nvidia/nv-embedqa-mistral-7b-v2",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/nvclip": {
"id": "nvidia/nvclip",
"name": "nvidia/nvclip",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/nvidia-nemotron-nano-9b-v2": {
"id": "nvidia/nvidia-nemotron-nano-9b-v2",
"name": "nvidia-nemotron-nano-9b-v2",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nvidia/riva-translate-4b-instruct": {
"id": "nvidia/riva-translate-4b-instruct",
"name": "nvidia/riva-translate-4b-instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/riva-translate-4b-instruct-v1.1": {
"id": "nvidia/riva-translate-4b-instruct-v1.1",
"name": "nvidia/riva-translate-4b-instruct-v1.1",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"nvidia/vila": {
"id": "nvidia/vila",
"name": "nvidia/vila",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"openai/gpt-oss-120b": {
"id": "openai/gpt-oss-120b",
"name": "GPT-OSS-120B",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
]
}
},
"openai/gpt-oss-20b": {
"id": "openai/gpt-oss-20b",
"name": "GPT OSS 20B",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
]
}
},
"qwen/qwen2.5-coder-32b-instruct": {
"id": "qwen/qwen2.5-coder-32b-instruct",
"name": "Qwen2.5 Coder 32b Instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"qwen/qwen2.5-coder-7b-instruct": {
"id": "qwen/qwen2.5-coder-7b-instruct",
"name": "Qwen2.5 Coder 7b Instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"qwen/qwen3-235b-a22b": {
"id": "qwen/qwen3-235b-a22b",
"name": "Qwen3 235B A22B",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3-coder-480b-a35b-instruct": {
"id": "qwen/qwen3-coder-480b-a35b-instruct",
"name": "Qwen3 Coder 480B A35B Instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 66536
},
"qwen/qwen3-next-80b-a3b-instruct": {
"id": "qwen/qwen3-next-80b-a3b-instruct",
"name": "Qwen3-Next-80B-A3B-Instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 16384
},
"qwen/qwen3-next-80b-a3b-thinking": {
"id": "qwen/qwen3-next-80b-a3b-thinking",
"name": "Qwen3 Next 80B A3B Thinking",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"qwen/qwen3.5-122b-a10b": {
"id": "qwen/qwen3.5-122b-a10b",
"name": "Qwen3.5 122B-A10B",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.5-397b-a17b": {
"id": "qwen/qwen3.5-397b-a17b",
"name": "Qwen3.5-397B-A17B",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"sarvamai/sarvam-m": {
"id": "sarvamai/sarvam-m",
"name": "sarvam-m",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"snowflake/arctic-embed-l": {
"id": "snowflake/arctic-embed-l",
"name": "snowflake/arctic-embed-l",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"stepfun-ai/step-3.5-flash": {
"id": "stepfun-ai/step-3.5-flash",
"name": "Step 3.5 Flash",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"stepfun-ai/step-3.7-flash": {
"id": "stepfun-ai/step-3.7-flash",
"name": "Step 3.7 Flash",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"stockmark/stockmark-2-100b-instruct": {
"id": "stockmark/stockmark-2-100b-instruct",
"name": "stockmark/stockmark-2-100b-instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"upstage/solar-10_7b-instruct": {
"id": "upstage/solar-10_7b-instruct",
"name": "solar-10.7b-instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"upstage/solar-10.7b-instruct": {
"id": "upstage/solar-10.7b-instruct",
"name": "upstage/solar-10.7b-instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"writer/palmyra-creative-122b": {
"id": "writer/palmyra-creative-122b",
"name": "writer/palmyra-creative-122b",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"writer/palmyra-fin-70b-32k": {
"id": "writer/palmyra-fin-70b-32k",
"name": "writer/palmyra-fin-70b-32k",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"writer/palmyra-med-70b": {
"id": "writer/palmyra-med-70b",
"name": "writer/palmyra-med-70b",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"writer/palmyra-med-70b-32k": {
"id": "writer/palmyra-med-70b-32k",
"name": "writer/palmyra-med-70b-32k",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
},
"z-ai/glm-5.1": {
"id": "z-ai/glm-5.1",
"name": "GLM-5.1",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"z-ai/glm4.7": {
"id": "z-ai/glm4.7",
"name": "GLM-4.7",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"z-ai/glm5": {
"id": "z-ai/glm5",
"name": "GLM5",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 131000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zyphra/zamba2-7b-instruct": {
"id": "zyphra/zamba2-7b-instruct",
"name": "zyphra/zamba2-7b-instruct",
"api": "openai-completions",
"provider": "nvidia",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null
}
},
"ollama-cloud": {
"cogito-2.1:671b": {
"id": "cogito-2.1:671b",
"name": "cogito-2.1:671b",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"deepseek-v3.1:671b": {
"id": "deepseek-v3.1:671b",
"name": "deepseek-v3.1:671b",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 163840,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"deepseek-v3.2": {
"id": "deepseek-v3.2",
"name": "deepseek-v3.2",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"deepseek-v4-flash": {
"id": "deepseek-v4-flash",
"name": "deepseek-v4-flash",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 1048576,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"deepseek-v4-pro": {
"id": "deepseek-v4-pro",
"name": "deepseek-v4-pro",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 1048576,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"devstral-2:123b": {
"id": "devstral-2:123b",
"name": "devstral-2:123b",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"devstral-small-2:24b": {
"id": "devstral-small-2:24b",
"name": "devstral-small-2:24b",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"gemini-3-flash-preview": {
"id": "gemini-3-flash-preview",
"name": "gemini-3-flash-preview",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"gemma4:31b": {
"id": "gemma4:31b",
"name": "gemma4:31b",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"glm-4.6": {
"id": "glm-4.6",
"name": "glm-4.6",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"glm-4.7": {
"id": "glm-4.7",
"name": "glm-4.7",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"glm-5": {
"id": "glm-5",
"name": "glm-5",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"glm-5.1": {
"id": "glm-5.1",
"name": "glm-5.1",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-oss:120b": {
"id": "gpt-oss:120b",
"name": "gpt-oss:120b",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-oss:20b": {
"id": "gpt-oss:20b",
"name": "gpt-oss:20b",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"kimi-k2-thinking": {
"id": "kimi-k2-thinking",
"name": "kimi-k2-thinking",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"kimi-k2:1t": {
"id": "kimi-k2:1t",
"name": "kimi-k2:1t",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"kimi-k2.5": {
"id": "kimi-k2.5",
"name": "kimi-k2.5",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"kimi-k2.6": {
"id": "kimi-k2.6",
"name": "kimi-k2.6",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"kimi-k2.7-code": {
"id": "kimi-k2.7-code",
"name": "kimi-k2.7-code",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"minimax-m2": {
"id": "minimax-m2",
"name": "minimax-m2",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax-m2.1": {
"id": "minimax-m2.1",
"name": "minimax-m2.1",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax-m2.5": {
"id": "minimax-m2.5",
"name": "minimax-m2.5",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax-m2.7": {
"id": "minimax-m2.7",
"name": "minimax-m2.7",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 196608,
"maxTokens": 196608,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax-m3": {
"id": "minimax-m3",
"name": "minimax-m3",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 512000,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"ministral-3:14b": {
"id": "ministral-3:14b",
"name": "ministral-3:14b",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 128000
},
"ministral-3:3b": {
"id": "ministral-3:3b",
"name": "ministral-3:3b",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 128000
},
"ministral-3:8b": {
"id": "ministral-3:8b",
"name": "ministral-3:8b",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 128000
},
"mistral-large-3:675b": {
"id": "mistral-large-3:675b",
"name": "mistral-large-3:675b",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"nemotron-3-nano:30b": {
"id": "nemotron-3-nano:30b",
"name": "nemotron-3-nano:30b",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"nemotron-3-super": {
"id": "nemotron-3-super",
"name": "nemotron-3-super",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"nemotron-3-ultra": {
"id": "nemotron-3-ultra",
"name": "nemotron-3-ultra",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen3-coder-next": {
"id": "qwen3-coder-next",
"name": "qwen3-coder-next",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536
},
"qwen3-coder:480b": {
"id": "qwen3-coder:480b",
"name": "qwen3-coder:480b",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536
},
"qwen3-next:80b": {
"id": "qwen3-next:80b",
"name": "qwen3-next:80b",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen3-vl:235b": {
"id": "qwen3-vl:235b",
"name": "qwen3-vl:235b",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen3-vl:235b-instruct": {
"id": "qwen3-vl:235b-instruct",
"name": "qwen3-vl:235b-instruct",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 131072
},
"qwen3.5:397b": {
"id": "qwen3.5:397b",
"name": "qwen3.5:397b",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"rnj-1:8b": {
"id": "rnj-1:8b",
"name": "rnj-1:8b",
"api": "ollama-chat",
"provider": "ollama-cloud",
"baseUrl": "https://ollama.com",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32768,
"maxTokens": 4096
}
},
"openai": {
"codex-mini-latest": {
"id": "codex-mini-latest",
"name": "Codex Mini",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.5,
"output": 6,
"cacheRead": 0.375,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-4": {
"id": "gpt-4",
"name": "GPT-4",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 30,
"output": 60,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 8192,
"maxTokens": 8192
},
"gpt-4-turbo": {
"id": "gpt-4-turbo",
"name": "GPT-4 Turbo",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 10,
"output": 30,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"gpt-4.1": {
"id": "gpt-4.1",
"name": "GPT-4.1",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 8,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 1047576,
"maxTokens": 32768
},
"gpt-4.1-mini": {
"id": "gpt-4.1-mini",
"name": "GPT-4.1 mini",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.4,
"output": 1.6,
"cacheRead": 0.1,
"cacheWrite": 0
},
"contextWindow": 1047576,
"maxTokens": 32768
},
"gpt-4.1-nano": {
"id": "gpt-4.1-nano",
"name": "GPT-4.1 nano",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1,
"output": 0.4,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 1047576,
"maxTokens": 32768
},
"gpt-4o": {
"id": "gpt-4o",
"name": "GPT-4o",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 10,
"cacheRead": 1.25,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"gpt-4o-2024-05-13": {
"id": "gpt-4o-2024-05-13",
"name": "GPT-4o (2024-05-13)",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"gpt-4o-2024-08-06": {
"id": "gpt-4o-2024-08-06",
"name": "GPT-4o (2024-08-06)",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 10,
"cacheRead": 1.25,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"gpt-4o-2024-11-20": {
"id": "gpt-4o-2024-11-20",
"name": "GPT-4o (2024-11-20)",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 10,
"cacheRead": 1.25,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"gpt-4o-mini": {
"id": "gpt-4o-mini",
"name": "GPT-4o mini",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0.075,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"gpt-5": {
"id": "gpt-5",
"name": "GPT-5",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"applyPatchToolType": "freeform",
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5-chat-latest": {
"id": "gpt-5-chat-latest",
"name": "GPT-5 Chat Latest",
"api": "openai-responses",
"baseUrl": "https://api.openai.com/v1",
"provider": "openai",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384,
"applyPatchToolType": "freeform"
},
"gpt-5-codex": {
"id": "gpt-5-codex",
"name": "GPT-5-Codex",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"applyPatchToolType": "freeform",
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5-mini": {
"id": "gpt-5-mini",
"name": "GPT-5 Mini",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 2,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"applyPatchToolType": "freeform",
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5-nano": {
"id": "gpt-5-nano",
"name": "GPT-5 Nano",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.05,
"output": 0.4,
"cacheRead": 0.005,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"applyPatchToolType": "freeform",
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5-pro": {
"id": "gpt-5-pro",
"name": "GPT-5 Pro",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 120,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 272000,
"applyPatchToolType": "freeform",
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5.1": {
"id": "gpt-5.1",
"name": "GPT-5.1",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"applyPatchToolType": "freeform",
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5.1-chat-latest": {
"id": "gpt-5.1-chat-latest",
"name": "GPT-5.1 Chat",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384,
"applyPatchToolType": "freeform",
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5.1-codex": {
"id": "gpt-5.1-codex",
"name": "GPT-5.1 Codex",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"applyPatchToolType": "freeform",
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5.1-codex-max": {
"id": "gpt-5.1-codex-max",
"name": "GPT-5.1 Codex Max",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"applyPatchToolType": "freeform",
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5.1-codex-mini": {
"id": "gpt-5.1-codex-mini",
"name": "GPT-5.1 Codex mini",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 2,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"applyPatchToolType": "freeform",
"thinking": {
"mode": "effort",
"efforts": [
"medium",
"high"
]
}
},
"gpt-5.2": {
"id": "gpt-5.2",
"name": "GPT-5.2",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"applyPatchToolType": "freeform",
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.2-chat-latest": {
"id": "gpt-5.2-chat-latest",
"name": "GPT-5.2 Chat",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384,
"applyPatchToolType": "freeform",
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.2-codex": {
"id": "gpt-5.2-codex",
"name": "GPT-5.2 Codex",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"applyPatchToolType": "freeform",
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.2-pro": {
"id": "gpt-5.2-pro",
"name": "GPT-5.2 Pro",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 21,
"output": 168,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"applyPatchToolType": "freeform",
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.3-chat-latest": {
"id": "gpt-5.3-chat-latest",
"name": "GPT-5.3 Chat",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384,
"applyPatchToolType": "freeform"
},
"gpt-5.3-codex": {
"id": "gpt-5.3-codex",
"name": "GPT-5.3 Codex",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"applyPatchToolType": "freeform",
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.3-codex-spark": {
"id": "gpt-5.3-codex-spark",
"name": "GPT-5.3 Codex Spark",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 32000,
"applyPatchToolType": "freeform",
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
},
"contextPromotionTarget": "openai/gpt-5.5"
},
"gpt-5.4": {
"id": "gpt-5.4",
"name": "GPT-5.4",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 15,
"cacheRead": 0.25,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 128000,
"applyPatchToolType": "freeform",
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.4-mini": {
"id": "gpt-5.4-mini",
"name": "GPT-5.4 mini",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.75,
"output": 4.5,
"cacheRead": 0.075,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"applyPatchToolType": "freeform",
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.4-nano": {
"id": "gpt-5.4-nano",
"name": "GPT-5.4 nano",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.2,
"output": 1.25,
"cacheRead": 0.02,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"applyPatchToolType": "freeform",
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.4-pro": {
"id": "gpt-5.4-pro",
"name": "GPT-5.4 Pro",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 30,
"output": 180,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 128000,
"applyPatchToolType": "freeform",
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.5": {
"id": "gpt-5.5",
"name": "GPT-5.5",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 30,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 128000,
"applyPatchToolType": "freeform",
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
},
"contextPromotionTarget": "openai/gpt-5.4"
},
"gpt-5.5-pro": {
"id": "gpt-5.5-pro",
"name": "GPT-5.5 Pro",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 30,
"output": 180,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 128000,
"applyPatchToolType": "freeform",
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
},
"contextPromotionTarget": "openai/gpt-5.4"
},
"o1": {
"id": "o1",
"name": "o1",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 60,
"cacheRead": 7.5,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"o1-pro": {
"id": "o1-pro",
"name": "o1-pro",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 150,
"output": 600,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"o3": {
"id": "o3",
"name": "o3",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 8,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"o3-deep-research": {
"id": "o3-deep-research",
"name": "o3-deep-research",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 10,
"output": 40,
"cacheRead": 2.5,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"o3-mini": {
"id": "o3-mini",
"name": "o3-mini",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.1,
"output": 4.4,
"cacheRead": 0.55,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"o3-pro": {
"id": "o3-pro",
"name": "o3-pro",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 20,
"output": 80,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"o4-mini": {
"id": "o4-mini",
"name": "o4-mini",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.1,
"output": 4.4,
"cacheRead": 0.275,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"o4-mini-deep-research": {
"id": "o4-mini-deep-research",
"name": "o4-mini-deep-research",
"api": "openai-responses",
"provider": "openai",
"baseUrl": "https://api.openai.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 8,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
}
},
"openai-codex": {
"codex-auto-review": {
"id": "codex-auto-review",
"name": "Codex Auto Review",
"api": "openai-codex-responses",
"provider": "openai-codex",
"baseUrl": "https://chatgpt.com/backend-api",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"preferWebsockets": true,
"priority": 43,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5": {
"id": "gpt-5",
"name": "GPT-5",
"api": "openai-codex-responses",
"provider": "openai-codex",
"baseUrl": "https://chatgpt.com/backend-api",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"preferWebsockets": true,
"priority": 16,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
},
"applyPatchToolType": "freeform"
},
"gpt-5-codex": {
"id": "gpt-5-codex",
"name": "GPT-5-Codex",
"api": "openai-codex-responses",
"provider": "openai-codex",
"baseUrl": "https://chatgpt.com/backend-api",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"preferWebsockets": true,
"priority": 15,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
},
"applyPatchToolType": "freeform"
},
"gpt-5-codex-mini": {
"id": "gpt-5-codex-mini",
"name": "gpt-5-codex-mini",
"api": "openai-codex-responses",
"provider": "openai-codex",
"baseUrl": "https://chatgpt.com/backend-api",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"preferWebsockets": true,
"priority": 20,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
},
"applyPatchToolType": "freeform"
},
"gpt-5.1": {
"id": "gpt-5.1",
"name": "GPT-5.1",
"api": "openai-codex-responses",
"provider": "openai-codex",
"baseUrl": "https://chatgpt.com/backend-api",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.13,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"preferWebsockets": true,
"priority": 12,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
},
"applyPatchToolType": "freeform"
},
"gpt-5.1-codex": {
"id": "gpt-5.1-codex",
"name": "GPT-5.1 Codex",
"api": "openai-codex-responses",
"provider": "openai-codex",
"baseUrl": "https://chatgpt.com/backend-api",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"preferWebsockets": true,
"priority": 11,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
},
"applyPatchToolType": "freeform"
},
"gpt-5.1-codex-max": {
"id": "gpt-5.1-codex-max",
"name": "GPT-5.1 Codex Max",
"api": "openai-codex-responses",
"provider": "openai-codex",
"baseUrl": "https://chatgpt.com/backend-api",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"preferWebsockets": true,
"priority": 10,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
},
"applyPatchToolType": "freeform"
},
"gpt-5.1-codex-mini": {
"id": "gpt-5.1-codex-mini",
"name": "GPT-5.1 Codex mini",
"api": "openai-codex-responses",
"provider": "openai-codex",
"baseUrl": "https://chatgpt.com/backend-api",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 2,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"preferWebsockets": true,
"priority": 19,
"thinking": {
"mode": "effort",
"efforts": [
"medium",
"high"
]
},
"applyPatchToolType": "freeform"
},
"gpt-5.2": {
"id": "gpt-5.2",
"name": "GPT-5.2",
"api": "openai-codex-responses",
"provider": "openai-codex",
"baseUrl": "https://chatgpt.com/backend-api",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"preferWebsockets": true,
"priority": 29,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
},
"applyPatchToolType": "freeform"
},
"gpt-5.2-codex": {
"id": "gpt-5.2-codex",
"name": "GPT-5.2 Codex",
"api": "openai-codex-responses",
"provider": "openai-codex",
"baseUrl": "https://chatgpt.com/backend-api",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"preferWebsockets": true,
"priority": 8,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
},
"applyPatchToolType": "freeform"
},
"gpt-5.3-codex": {
"id": "gpt-5.3-codex",
"name": "GPT-5.3 Codex",
"api": "openai-codex-responses",
"provider": "openai-codex",
"baseUrl": "https://chatgpt.com/backend-api",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"preferWebsockets": true,
"priority": 25,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
},
"applyPatchToolType": "freeform"
},
"gpt-5.3-codex-spark": {
"id": "gpt-5.3-codex-spark",
"name": "GPT-5.3 Codex Spark",
"api": "openai-codex-responses",
"provider": "openai-codex",
"baseUrl": "https://chatgpt.com/backend-api",
"reasoning": true,
"preferWebsockets": true,
"input": [
"text"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 128000,
"contextPromotionTarget": "openai-codex/gpt-5.5",
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
},
"applyPatchToolType": "freeform"
},
"gpt-5.4": {
"id": "gpt-5.4",
"name": "GPT-5.4",
"api": "openai-codex-responses",
"provider": "openai-codex",
"baseUrl": "https://chatgpt.com/backend-api",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 15,
"cacheRead": 0.25,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"preferWebsockets": true,
"priority": 0,
"applyPatchToolType": "freeform",
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.4-mini": {
"id": "gpt-5.4-mini",
"name": "GPT-5.4 mini",
"api": "openai-codex-responses",
"provider": "openai-codex",
"baseUrl": "https://chatgpt.com/backend-api",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.75,
"output": 4.5,
"cacheRead": 0.075,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"preferWebsockets": true,
"priority": 1,
"applyPatchToolType": "freeform",
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.4-nano": {
"id": "gpt-5.4-nano",
"name": "GPT-5.4 nano",
"api": "openai-codex-responses",
"provider": "openai-codex",
"baseUrl": "https://chatgpt.com/backend-api",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.2,
"output": 1.25,
"cacheRead": 0.02,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"preferWebsockets": true,
"priority": 2,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
},
"applyPatchToolType": "freeform"
},
"gpt-5.5": {
"id": "gpt-5.5",
"name": "GPT-5.5",
"api": "openai-codex-responses",
"provider": "openai-codex",
"baseUrl": "https://chatgpt.com/backend-api",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 30,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"preferWebsockets": true,
"priority": 9,
"applyPatchToolType": "freeform",
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
},
"contextPromotionTarget": "openai-codex/gpt-5.4"
}
},
"opencode": {
"glm-5-free": {
"id": "glm-5-free",
"name": "GLM-5 Free",
"api": "openai-completions",
"provider": "opencode",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.3-codex-spark": {
"id": "gpt-5.3-codex-spark",
"name": "GPT-5.3 Codex Spark",
"api": "openai-responses",
"provider": "opencode",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.4": {
"id": "gpt-5.4",
"name": "GPT-5.4",
"api": "openai-responses",
"provider": "opencode",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 15,
"cacheRead": 0.25,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.4-pro": {
"id": "gpt-5.4-pro",
"name": "GPT-5.4 Pro",
"api": "openai-responses",
"provider": "opencode",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 30,
"output": 180,
"cacheRead": 30,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"kimi-k2.5-free": {
"id": "kimi-k2.5-free",
"name": "Kimi K2.5 Free",
"api": "openai-completions",
"provider": "opencode",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
}
},
"opencode-go": {
"deepseek-v4-flash": {
"id": "deepseek-v4-flash",
"name": "DeepSeek V4 Flash",
"api": "openai-completions",
"provider": "opencode-go",
"baseUrl": "https://opencode.ai/zen/go/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.14,
"output": 0.28,
"cacheRead": 0.0028,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 384000,
"compat": {
"supportsToolChoice": false,
"reasoningContentField": "reasoning_content",
"requiresReasoningContentForToolCalls": true
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek-v4-pro": {
"id": "deepseek-v4-pro",
"name": "DeepSeek V4 Pro",
"api": "openai-completions",
"provider": "opencode-go",
"baseUrl": "https://opencode.ai/zen/go/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.74,
"output": 3.48,
"cacheRead": 0.0145,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 384000,
"compat": {
"supportsToolChoice": false,
"reasoningContentField": "reasoning_content",
"requiresReasoningContentForToolCalls": true
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"glm-5": {
"id": "glm-5",
"name": "GLM-5",
"api": "openai-completions",
"provider": "opencode-go",
"baseUrl": "https://opencode.ai/zen/go/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 3.2,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"glm-5.1": {
"id": "glm-5.1",
"name": "GLM-5.1",
"api": "openai-completions",
"provider": "opencode-go",
"baseUrl": "https://opencode.ai/zen/go/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.4,
"output": 4.4,
"cacheRead": 0.26,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"kimi-k2.5": {
"id": "kimi-k2.5",
"name": "Kimi K2.5",
"api": "openai-completions",
"provider": "opencode-go",
"baseUrl": "https://opencode.ai/zen/go/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.6,
"output": 3,
"cacheRead": 0.1,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"kimi-k2.6": {
"id": "kimi-k2.6",
"name": "Kimi K2.6",
"api": "openai-completions",
"provider": "opencode-go",
"baseUrl": "https://opencode.ai/zen/go/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.95,
"output": 4,
"cacheRead": 0.16,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"kimi-k2.7-code": {
"id": "kimi-k2.7-code",
"name": "Kimi K2.7 Code",
"api": "openai-completions",
"provider": "opencode-go",
"baseUrl": "https://opencode.ai/zen/go/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.95,
"output": 4,
"cacheRead": 0.19,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"compat": {
"supportsForcedToolChoice": false
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"mimo-v2-omni": {
"id": "mimo-v2-omni",
"name": "MiMo-V2-Omni",
"api": "openai-completions",
"provider": "opencode-go",
"baseUrl": "https://opencode.ai/zen/go/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.4,
"output": 2,
"cacheRead": 0.08,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
},
"compat": {
"supportsToolChoice": false
}
},
"mimo-v2-pro": {
"id": "mimo-v2-pro",
"name": "MiMo-V2-Pro",
"api": "openai-completions",
"provider": "opencode-go",
"baseUrl": "https://opencode.ai/zen/go/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 3,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
},
"compat": {
"supportsToolChoice": false
}
},
"mimo-v2.5": {
"id": "mimo-v2.5",
"name": "MiMo V2.5",
"api": "openai-completions",
"provider": "opencode-go",
"baseUrl": "https://opencode.ai/zen/go/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.14,
"output": 0.28,
"cacheRead": 0.0028,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"compat": {
"supportsToolChoice": false
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"mimo-v2.5-pro": {
"id": "mimo-v2.5-pro",
"name": "MiMo V2.5 Pro",
"api": "openai-completions",
"provider": "opencode-go",
"baseUrl": "https://opencode.ai/zen/go/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.74,
"output": 3.48,
"cacheRead": 0.0145,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 128000,
"compat": {
"supportsToolChoice": false
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"minimax-m2.5": {
"id": "minimax-m2.5",
"name": "MiniMax M2.5",
"api": "anthropic-messages",
"provider": "opencode-go",
"baseUrl": "https://opencode.ai/zen/go",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.03,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"minimax-m2.7": {
"id": "minimax-m2.7",
"name": "MiniMax M2.7",
"api": "openai-completions",
"provider": "opencode-go",
"baseUrl": "https://opencode.ai/zen/go/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.06,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax-m3": {
"id": "minimax-m3",
"name": "MiniMax M3 (3x usage)",
"api": "openai-completions",
"provider": "opencode-go",
"baseUrl": "https://opencode.ai/zen/go/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1,
"output": 0.4,
"cacheRead": 0.02,
"cacheWrite": 0
},
"contextWindow": 512000,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"qwen3.5-plus": {
"id": "qwen3.5-plus",
"name": "Qwen3.5 Plus",
"api": "openai-completions",
"provider": "opencode-go",
"baseUrl": "https://opencode.ai/zen/go/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.2,
"output": 1.2,
"cacheRead": 0.02,
"cacheWrite": 0.25
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen3.6-plus": {
"id": "qwen3.6-plus",
"name": "Qwen3.6 Plus",
"api": "openai-completions",
"provider": "opencode-go",
"baseUrl": "https://opencode.ai/zen/go/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.5,
"output": 3,
"cacheRead": 0.05,
"cacheWrite": 0.625
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen3.7-max": {
"id": "qwen3.7-max",
"name": "Qwen3.7 Max",
"api": "anthropic-messages",
"provider": "opencode-go",
"baseUrl": "https://opencode.ai/zen/go",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 2.5,
"output": 7.5,
"cacheRead": 0.5,
"cacheWrite": 3.125
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"qwen3.7-plus": {
"id": "qwen3.7-plus",
"name": "Qwen3.7 Plus",
"api": "anthropic-messages",
"provider": "opencode-go",
"baseUrl": "https://opencode.ai/zen/go",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.4,
"output": 1.6,
"cacheRead": 0.04,
"cacheWrite": 0.5
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
}
},
"opencode-zen": {
"big-pickle": {
"id": "big-pickle",
"name": "Big Pickle",
"api": "openai-completions",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"claude-3-5-haiku": {
"id": "claude-3-5-haiku",
"name": "Claude Haiku 3.5",
"api": "anthropic-messages",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.8,
"output": 4,
"cacheRead": 0.08,
"cacheWrite": 1
},
"contextWindow": 200000,
"maxTokens": 8192
},
"claude-fable-5": {
"id": "claude-fable-5",
"name": "Claude Fable 5",
"api": "anthropic-messages",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 10,
"output": 50,
"cacheRead": 1,
"cacheWrite": 12.5
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"low": "medium",
"medium": "high",
"high": "xhigh",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"claude-haiku-4-5": {
"id": "claude-haiku-4-5",
"name": "Claude Haiku 4.5",
"api": "anthropic-messages",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1,
"output": 5,
"cacheRead": 0.1,
"cacheWrite": 1.25
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-opus-4-1": {
"id": "claude-opus-4-1",
"name": "Claude Opus 4.1",
"api": "anthropic-messages",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 75,
"cacheRead": 1.5,
"cacheWrite": 18.75
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-opus-4-5": {
"id": "claude-opus-4-5",
"name": "Claude Opus 4.5",
"api": "anthropic-messages",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "anthropic-budget-effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-opus-4-6": {
"id": "claude-opus-4-6",
"name": "Claude Opus 4.6",
"api": "anthropic-messages",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"xhigh": "max"
}
}
},
"claude-opus-4-7": {
"id": "claude-opus-4-7",
"name": "Claude Opus 4.7",
"api": "anthropic-messages",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"low": "medium",
"medium": "high",
"high": "xhigh",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"claude-opus-4-8": {
"id": "claude-opus-4-8",
"name": "Claude Opus 4.8",
"api": "anthropic-messages",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"low": "medium",
"medium": "high",
"high": "xhigh",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"claude-sonnet-4": {
"id": "claude-sonnet-4",
"name": "Claude Sonnet 4",
"api": "anthropic-messages",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-sonnet-4-5": {
"id": "claude-sonnet-4-5",
"name": "Claude Sonnet 4.5",
"api": "anthropic-messages",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "anthropic-budget-effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-sonnet-4-6": {
"id": "claude-sonnet-4-6",
"name": "Claude Sonnet 4.6",
"api": "anthropic-messages",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortMap": {
"minimal": "low"
}
}
},
"deepseek-v4-flash": {
"id": "deepseek-v4-flash",
"name": "DeepSeek V4 Flash",
"api": "openai-completions",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.14,
"output": 0.28,
"cacheRead": 0.028,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 384000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek-v4-flash-free": {
"id": "deepseek-v4-flash-free",
"name": "DeepSeek V4 Flash Free",
"api": "openai-completions",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek-v4-pro": {
"id": "deepseek-v4-pro",
"name": "DeepSeek V4 Pro",
"api": "openai-completions",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.74,
"output": 3.84,
"cacheRead": 0.145,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 384000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"gemini-3-flash": {
"id": "gemini-3-flash",
"name": "Gemini 3 Flash",
"api": "google-generative-ai",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.5,
"output": 3,
"cacheRead": 0.05,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "google-level",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"gemini-3-pro": {
"id": "gemini-3-pro",
"name": "Gemini 3 Pro",
"api": "google-generative-ai",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 12,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "google-level",
"efforts": [
"low",
"high"
],
"requiresEffort": true
}
},
"gemini-3.1-pro": {
"id": "gemini-3.1-pro",
"name": "Gemini 3.1 Pro Preview",
"api": "google-generative-ai",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 12,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "google-level",
"efforts": [
"low",
"high"
],
"requiresEffort": true
}
},
"gemini-3.5-flash": {
"id": "gemini-3.5-flash",
"name": "Gemini 3.5 Flash",
"api": "google-generative-ai",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.5,
"output": 9,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "google-level",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"glm-4.6": {
"id": "glm-4.6",
"name": "glm-4.6",
"api": "openai-completions",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.2,
"cacheRead": 0.1,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"glm-4.7": {
"id": "glm-4.7",
"name": "GLM-4.7",
"api": "openai-completions",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.2,
"cacheRead": 0.1,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"glm-5": {
"id": "glm-5",
"name": "GLM-5",
"api": "openai-completions",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 3.2,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"glm-5.1": {
"id": "glm-5.1",
"name": "GLM-5.1",
"api": "openai-completions",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.4,
"output": 4.4,
"cacheRead": 0.26,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5": {
"id": "gpt-5",
"name": "GPT-5",
"api": "openai-responses",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.07,
"output": 8.5,
"cacheRead": 0.107,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5-codex": {
"id": "gpt-5-codex",
"name": "GPT-5 Codex",
"api": "openai-responses",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.07,
"output": 8.5,
"cacheRead": 0.107,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5-nano": {
"id": "gpt-5-nano",
"name": "GPT-5 Nano",
"api": "openai-responses",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.05,
"output": 0.4,
"cacheRead": 0.005,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5.1": {
"id": "gpt-5.1",
"name": "GPT-5.1",
"api": "openai-responses",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.07,
"output": 8.5,
"cacheRead": 0.107,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5.1-codex": {
"id": "gpt-5.1-codex",
"name": "GPT-5.1 Codex",
"api": "openai-responses",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.07,
"output": 8.5,
"cacheRead": 0.107,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5.1-codex-max": {
"id": "gpt-5.1-codex-max",
"name": "GPT-5.1 Codex Max",
"api": "openai-responses",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"gpt-5.1-codex-mini": {
"id": "gpt-5.1-codex-mini",
"name": "GPT-5.1 Codex Mini",
"api": "openai-responses",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 2,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"medium",
"high"
]
}
},
"gpt-5.2": {
"id": "gpt-5.2",
"name": "GPT-5.2",
"api": "openai-responses",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.2-codex": {
"id": "gpt-5.2-codex",
"name": "GPT-5.2 Codex",
"api": "openai-responses",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.3-codex": {
"id": "gpt-5.3-codex",
"name": "GPT-5.3 Codex",
"api": "openai-responses",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.3-codex-spark": {
"id": "gpt-5.3-codex-spark",
"name": "GPT-5.3 Codex Spark",
"api": "openai-responses",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
},
"contextPromotionTarget": "opencode-zen/gpt-5.5"
},
"gpt-5.4": {
"id": "gpt-5.4",
"name": "GPT-5.4",
"api": "openai-responses",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 15,
"cacheRead": 0.25,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.4-mini": {
"id": "gpt-5.4-mini",
"name": "GPT-5.4 Mini",
"api": "openai-responses",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.75,
"output": 4.5,
"cacheRead": 0.075,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.4-nano": {
"id": "gpt-5.4-nano",
"name": "GPT-5.4 Nano",
"api": "openai-responses",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.2,
"output": 1.25,
"cacheRead": 0.02,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.4-pro": {
"id": "gpt-5.4-pro",
"name": "GPT-5.4 Pro",
"api": "openai-responses",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 30,
"output": 180,
"cacheRead": 30,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"gpt-5.5": {
"id": "gpt-5.5",
"name": "GPT-5.5",
"api": "openai-responses",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 30,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
},
"contextPromotionTarget": "opencode-zen/gpt-5.4"
},
"gpt-5.5-pro": {
"id": "gpt-5.5-pro",
"name": "GPT-5.5 Pro",
"api": "openai-responses",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 30,
"output": 180,
"cacheRead": 30,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
},
"contextPromotionTarget": "opencode-zen/gpt-5.4"
},
"grok-build-0.1": {
"id": "grok-build-0.1",
"name": "Grok Build 0.1",
"api": "openai-completions",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1,
"output": 2,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"hy3-preview-free": {
"id": "hy3-preview-free",
"name": "Hy3 preview Free",
"api": "openai-completions",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"kimi-k2": {
"id": "kimi-k2",
"name": "Kimi K2",
"api": "openai-completions",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.4,
"output": 2.5,
"cacheRead": 0.4,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortRouting": {
"off": "kimi-k2",
"minimal": "kimi-k2-thinking",
"low": "kimi-k2-thinking",
"medium": "kimi-k2-thinking",
"high": "kimi-k2-thinking",
"xhigh": "kimi-k2-thinking"
}
}
},
"kimi-k2.5": {
"id": "kimi-k2.5",
"name": "Kimi K2.5",
"api": "openai-completions",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.6,
"output": 3,
"cacheRead": 0.08,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"kimi-k2.6": {
"id": "kimi-k2.6",
"name": "Kimi K2.6",
"api": "openai-completions",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.95,
"output": 4,
"cacheRead": 0.16,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"ling-2.6-flash-free": {
"id": "ling-2.6-flash-free",
"name": "Ling 2.6 Flash Free",
"api": "openai-completions",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262100,
"maxTokens": 32800
},
"mimo-v2-flash-free": {
"id": "mimo-v2-flash-free",
"name": "MiMo V2 Flash Free",
"api": "openai-completions",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"mimo-v2-omni-free": {
"id": "mimo-v2-omni-free",
"name": "MiMo V2 Omni Free",
"api": "openai-completions",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"mimo-v2-pro-free": {
"id": "mimo-v2-pro-free",
"name": "MiMo V2 Pro Free",
"api": "openai-completions",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"mimo-v2.5-free": {
"id": "mimo-v2.5-free",
"name": "MiMo V2.5 Free",
"api": "openai-completions",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"minimax-m2.1": {
"id": "minimax-m2.1",
"name": "minimax-m2.1",
"api": "openai-completions",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.1,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax-m2.5": {
"id": "minimax-m2.5",
"name": "MiniMax M2.5",
"api": "openai-completions",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.06,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax-m2.5-free": {
"id": "minimax-m2.5-free",
"name": "MiniMax M2.5 Free",
"api": "anthropic-messages",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"minimax-m2.7": {
"id": "minimax-m2.7",
"name": "MiniMax M2.7",
"api": "openai-completions",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.06,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax-m3-free": {
"id": "minimax-m3-free",
"name": "MiniMax M3 Free",
"api": "openai-completions",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nemotron-3-super-free": {
"id": "nemotron-3-super-free",
"name": "Nemotron 3 Super Free",
"api": "openai-completions",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nemotron-3-ultra-free": {
"id": "nemotron-3-ultra-free",
"name": "Nemotron 3 Ultra Free",
"api": "openai-completions",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"north-mini-code-free": {
"id": "north-mini-code-free",
"name": "North Mini Code Free",
"api": "openai-completions",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"qwen3.5-plus": {
"id": "qwen3.5-plus",
"name": "Qwen3.5 Plus",
"api": "anthropic-messages",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.2,
"output": 1.2,
"cacheRead": 0.02,
"cacheWrite": 0.25
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"qwen3.6-plus": {
"id": "qwen3.6-plus",
"name": "Qwen3.6 Plus",
"api": "anthropic-messages",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.5,
"output": 3,
"cacheRead": 0.05,
"cacheWrite": 0.625
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"qwen3.6-plus-free": {
"id": "qwen3.6-plus-free",
"name": "Qwen3.6 Plus Free",
"api": "openai-completions",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"ring-2.6-1t-free": {
"id": "ring-2.6-1t-free",
"name": "Ring 2.6 1T Free",
"api": "openai-completions",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262000,
"maxTokens": 66000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"trinity-large-preview-free": {
"id": "trinity-large-preview-free",
"name": "Trinity Large Preview",
"api": "openai-completions",
"provider": "opencode-zen",
"baseUrl": "https://opencode.ai/zen/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072
}
},
"openrouter": {
"~anthropic/claude-fable-latest": {
"id": "~anthropic/claude-fable-latest",
"name": "Claude Fable Latest",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 10,
"output": 50,
"cacheRead": 1,
"cacheWrite": 12.5
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"~anthropic/claude-haiku-latest": {
"id": "~anthropic/claude-haiku-latest",
"name": "Claude Haiku Latest",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1,
"output": 5,
"cacheRead": 0.09999999999999999,
"cacheWrite": 1.25
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"~anthropic/claude-opus-latest": {
"id": "~anthropic/claude-opus-latest",
"name": "Claude Opus Latest",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"~anthropic/claude-sonnet-latest": {
"id": "~anthropic/claude-sonnet-latest",
"name": "Claude Sonnet Latest",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"~google/gemini-flash-latest": {
"id": "~google/gemini-flash-latest",
"name": "Gemini Flash Latest",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.5,
"output": 9,
"cacheRead": 0.15,
"cacheWrite": 0.08333333333333334
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"~google/gemini-pro-latest": {
"id": "~google/gemini-pro-latest",
"name": "Gemini Pro Latest",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 12,
"cacheRead": 0.19999999999999998,
"cacheWrite": 0.375
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"~moonshotai/kimi-latest": {
"id": "~moonshotai/kimi-latest",
"name": "Kimi Latest",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.6799999999999999,
"output": 3.41,
"cacheRead": 0.33999999999999997,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262142,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"~openai/gpt-latest": {
"id": "~openai/gpt-latest",
"name": "GPT Latest",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 30,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"~openai/gpt-mini-latest": {
"id": "~openai/gpt-mini-latest",
"name": "GPT Mini Latest",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.75,
"output": 4.5,
"cacheRead": 0.075,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"ai21/jamba-large-1.7": {
"id": "ai21/jamba-large-1.7",
"name": "Jamba Large 1.7",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 2,
"output": 8,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 4096
},
"alibaba/tongyi-deepresearch-30b-a3b": {
"id": "alibaba/tongyi-deepresearch-30b-a3b",
"name": "Tongyi DeepResearch 30B A3B",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.09,
"output": 0.44999999999999996,
"cacheRead": 0.09,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"allenai/olmo-3.1-32b-instruct": {
"id": "allenai/olmo-3.1-32b-instruct",
"name": "Olmo 3.1 32B Instruct",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.19999999999999998,
"output": 0.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 65536,
"maxTokens": 16384
},
"amazon/nova-2-lite-v1": {
"id": "amazon/nova-2-lite-v1",
"name": "Nova 2 Lite",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 2.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65535,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"amazon/nova-lite-v1": {
"id": "amazon/nova-lite-v1",
"name": "Nova Lite 1.0",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.06,
"output": 0.24,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 300000,
"maxTokens": 5120,
"compat": {
"supportsToolChoice": false
}
},
"amazon/nova-micro-v1": {
"id": "amazon/nova-micro-v1",
"name": "Nova Micro 1.0",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.035,
"output": 0.14,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 5120,
"compat": {
"supportsToolChoice": false
}
},
"amazon/nova-premier-v1": {
"id": "amazon/nova-premier-v1",
"name": "Nova Premier 1.0",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 12.5,
"cacheRead": 0.625,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 32000,
"compat": {
"supportsToolChoice": false
}
},
"amazon/nova-pro-v1": {
"id": "amazon/nova-pro-v1",
"name": "Nova Pro 1.0",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.7999999999999999,
"output": 3.1999999999999997,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 300000,
"maxTokens": 5120,
"compat": {
"supportsToolChoice": false
}
},
"anthropic/claude-3-haiku": {
"id": "anthropic/claude-3-haiku",
"name": "Claude Haiku 3",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 1.25,
"cacheRead": 0.03,
"cacheWrite": 0.3
},
"contextWindow": 200000,
"maxTokens": 4096
},
"anthropic/claude-3.5-haiku": {
"id": "anthropic/claude-3.5-haiku",
"name": "Claude 3.5 Haiku",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.7999999999999999,
"output": 4,
"cacheRead": 0.08,
"cacheWrite": 1
},
"contextWindow": 200000,
"maxTokens": 8192
},
"anthropic/claude-3.5-sonnet": {
"id": "anthropic/claude-3.5-sonnet",
"name": "Claude Sonnet 3.5 v2",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 6,
"output": 30,
"cacheRead": 0.6,
"cacheWrite": 7.5
},
"contextWindow": 200000,
"maxTokens": 8192
},
"anthropic/claude-3.7-sonnet": {
"id": "anthropic/claude-3.7-sonnet",
"name": "Claude 3.7 Sonnet",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"anthropic/claude-3.7-sonnet:thinking": {
"id": "anthropic/claude-3.7-sonnet:thinking",
"name": "Claude 3.7 Sonnet (thinking)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"anthropic/claude-fable-5": {
"id": "anthropic/claude-fable-5",
"name": "Claude Fable 5",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 10,
"output": 50,
"cacheRead": 1,
"cacheWrite": 12.5
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"low": "medium",
"medium": "high",
"high": "xhigh",
"xhigh": "max"
}
}
},
"anthropic/claude-haiku-4.5": {
"id": "anthropic/claude-haiku-4.5",
"name": "Claude Haiku 4.5",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1,
"output": 5,
"cacheRead": 0.09999999999999999,
"cacheWrite": 1.25
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"anthropic/claude-opus-4": {
"id": "anthropic/claude-opus-4",
"name": "Claude Opus 4",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 75,
"cacheRead": 1.5,
"cacheWrite": 18.75
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"anthropic/claude-opus-4.1": {
"id": "anthropic/claude-opus-4.1",
"name": "Claude Opus 4.1",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 75,
"cacheRead": 1.5,
"cacheWrite": 18.75
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"anthropic/claude-opus-4.5": {
"id": "anthropic/claude-opus-4.5",
"name": "Claude Opus 4.5",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"anthropic/claude-opus-4.6": {
"id": "anthropic/claude-opus-4.6",
"name": "Claude Opus 4.6",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"xhigh": "max"
}
}
},
"anthropic/claude-opus-4.6-fast": {
"id": "anthropic/claude-opus-4.6-fast",
"name": "Claude Opus 4.6 (Fast)",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 30,
"output": 150,
"cacheRead": 3,
"cacheWrite": 37.5
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"xhigh": "max"
}
}
},
"anthropic/claude-opus-4.7": {
"id": "anthropic/claude-opus-4.7",
"name": "Claude Opus 4.7",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"low": "medium",
"medium": "high",
"high": "xhigh",
"xhigh": "max"
}
}
},
"anthropic/claude-opus-4.7-fast": {
"id": "anthropic/claude-opus-4.7-fast",
"name": "Claude Opus 4.7 (Fast)",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 30,
"output": 150,
"cacheRead": 3,
"cacheWrite": 37.5
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"low": "medium",
"medium": "high",
"high": "xhigh",
"xhigh": "max"
}
}
},
"anthropic/claude-opus-4.8": {
"id": "anthropic/claude-opus-4.8",
"name": "Claude Opus 4.8",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"low": "medium",
"medium": "high",
"high": "xhigh",
"xhigh": "max"
}
}
},
"anthropic/claude-opus-4.8-fast": {
"id": "anthropic/claude-opus-4.8-fast",
"name": "Claude Opus 4.8 (Fast)",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 10,
"output": 50,
"cacheRead": 1,
"cacheWrite": 12.5
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"low": "medium",
"medium": "high",
"high": "xhigh",
"xhigh": "max"
}
}
},
"anthropic/claude-sonnet-4": {
"id": "anthropic/claude-sonnet-4",
"name": "Claude Sonnet 4",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"anthropic/claude-sonnet-4.5": {
"id": "anthropic/claude-sonnet-4.5",
"name": "Claude Sonnet 4.5",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"anthropic/claude-sonnet-4.6": {
"id": "anthropic/claude-sonnet-4.6",
"name": "Claude Sonnet 4.6",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"arcee-ai/trinity-large-preview": {
"id": "arcee-ai/trinity-large-preview",
"name": "Trinity Large Preview",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.44999999999999996,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131000,
"maxTokens": 131000,
"compat": {
"supportsToolChoice": false
}
},
"arcee-ai/trinity-large-preview:free": {
"id": "arcee-ai/trinity-large-preview:free",
"name": "Trinity Large Preview (free)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131000,
"maxTokens": 131000,
"compat": {
"supportsToolChoice": false
}
},
"arcee-ai/trinity-large-thinking": {
"id": "arcee-ai/trinity-large-thinking",
"name": "Trinity Large Thinking",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.22,
"output": 0.85,
"cacheRead": 0.06,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"arcee-ai/trinity-large-thinking:free": {
"id": "arcee-ai/trinity-large-thinking:free",
"name": "Trinity Large Thinking (free)",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 80000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"arcee-ai/trinity-mini": {
"id": "arcee-ai/trinity-mini",
"name": "Trinity Mini",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.045,
"output": 0.15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"arcee-ai/trinity-mini:free": {
"id": "arcee-ai/trinity-mini:free",
"name": "Trinity Mini (free)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"arcee-ai/virtuoso-large": {
"id": "arcee-ai/virtuoso-large",
"name": "Virtuoso Large",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.75,
"output": 1.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 64000
},
"auto": {
"id": "auto",
"name": "Auto",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 30000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"baidu/cobuddy:free": {
"id": "baidu/cobuddy:free",
"name": "CoBuddy (free)",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
},
"compat": {
"supportsToolChoice": false
}
},
"baidu/ernie-4.5-21b-a3b": {
"id": "baidu/ernie-4.5-21b-a3b",
"name": "ERNIE 4.5 21B A3B",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.07,
"output": 0.28,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8000
},
"baidu/ernie-4.5-vl-28b-a3b": {
"id": "baidu/ernie-4.5-vl-28b-a3b",
"name": "ERNIE 4.5 VL 28B A3B",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.14,
"output": 0.56,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"bytedance-seed/seed-1.6": {
"id": "bytedance-seed/seed-1.6",
"name": "Seed 1.6",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"bytedance-seed/seed-1.6-flash": {
"id": "bytedance-seed/seed-1.6-flash",
"name": "Seed 1.6 Flash",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.075,
"output": 0.3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"bytedance-seed/seed-2.0-lite": {
"id": "bytedance-seed/seed-2.0-lite",
"name": "Seed-2.0-Lite",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"bytedance-seed/seed-2.0-mini": {
"id": "bytedance-seed/seed-2.0-mini",
"name": "Seed-2.0-Mini",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.09999999999999999,
"output": 0.39999999999999997,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"cohere/command-r-08-2024": {
"id": "cohere/command-r-08-2024",
"name": "Command R (08-2024)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4000
},
"cohere/command-r-plus-08-2024": {
"id": "cohere/command-r-plus-08-2024",
"name": "Command R+",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 2.5,
"output": 10,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4000
},
"deepseek/deepseek-chat": {
"id": "deepseek/deepseek-chat",
"name": "DeepSeek V3",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.20020000000000002,
"output": 0.8000999999999999,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16000
},
"deepseek/deepseek-chat-v3-0324": {
"id": "deepseek/deepseek-chat-v3-0324",
"name": "DeepSeek V3 0324",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.19999999999999998,
"output": 0.77,
"cacheRead": 0.135,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high"
}
}
},
"deepseek/deepseek-chat-v3.1": {
"id": "deepseek/deepseek-chat-v3.1",
"name": "DeepSeek V3.1",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.21,
"output": 0.7899999999999999,
"cacheRead": 0.13,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high"
}
}
},
"deepseek/deepseek-r1": {
"id": "deepseek/deepseek-r1",
"name": "R1",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.7,
"output": 2.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 16000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high"
}
}
},
"deepseek/deepseek-r1-0528": {
"id": "deepseek/deepseek-r1-0528",
"name": "R1 0528",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.5,
"output": 2.1500000000000004,
"cacheRead": 0.35,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high"
}
}
},
"deepseek/deepseek-v3.1-terminus": {
"id": "deepseek/deepseek-v3.1-terminus",
"name": "DeepSeek V3.1 Terminus",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.27,
"output": 0.95,
"cacheRead": 0.13,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high"
}
}
},
"deepseek/deepseek-v3.1-terminus:exacto": {
"id": "deepseek/deepseek-v3.1-terminus:exacto",
"name": "DeepSeek V3.1 Terminus (exacto)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.21,
"output": 0.7899999999999999,
"cacheRead": 0.16799999999999998,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high"
}
}
},
"deepseek/deepseek-v3.2": {
"id": "deepseek/deepseek-v3.2",
"name": "DeepSeek V3.2",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.2288,
"output": 0.3432,
"cacheRead": 0.0252,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high"
}
}
},
"deepseek/deepseek-v3.2-exp": {
"id": "deepseek/deepseek-v3.2-exp",
"name": "DeepSeek V3.2 Exp",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.27,
"output": 0.41,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high"
}
}
},
"deepseek/deepseek-v4-flash": {
"id": "deepseek/deepseek-v4-flash",
"name": "DeepSeek V4 Flash",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.09,
"output": 0.18,
"cacheRead": 0.02,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high"
}
}
},
"deepseek/deepseek-v4-flash:free": {
"id": "deepseek/deepseek-v4-flash:free",
"name": "DeepSeek V4 Flash (free)",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 384000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high"
}
}
},
"deepseek/deepseek-v4-pro": {
"id": "deepseek/deepseek-v4-pro",
"name": "DeepSeek V4 Pro",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.435,
"output": 0.87,
"cacheRead": 0.003625,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 384000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high"
}
}
},
"essentialai/rnj-1-instruct": {
"id": "essentialai/rnj-1-instruct",
"name": "Rnj 1 Instruct",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32768,
"maxTokens": 32768
},
"google/gemini-2.0-flash-001": {
"id": "google/gemini-2.0-flash-001",
"name": "Gemini 2.0 Flash",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.09999999999999999,
"output": 0.39999999999999997,
"cacheRead": 0.024999999999999998,
"cacheWrite": 0.08333333333333334
},
"contextWindow": 1000000,
"maxTokens": 8192
},
"google/gemini-2.0-flash-lite-001": {
"id": "google/gemini-2.0-flash-lite-001",
"name": "Gemini 2.0 Flash Lite",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.075,
"output": 0.3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 8192
},
"google/gemini-2.5-flash": {
"id": "google/gemini-2.5-flash",
"name": "Gemini 2.5 Flash",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 2.5,
"cacheRead": 0.03,
"cacheWrite": 0.08333333333333334
},
"contextWindow": 1048576,
"maxTokens": 65535,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"google/gemini-2.5-flash-lite": {
"id": "google/gemini-2.5-flash-lite",
"name": "Gemini 2.5 Flash Lite",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.09999999999999999,
"output": 0.39999999999999997,
"cacheRead": 0.01,
"cacheWrite": 0.08333333333333334
},
"contextWindow": 1048576,
"maxTokens": 65535,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"google/gemini-2.5-flash-lite-preview-09-2025": {
"id": "google/gemini-2.5-flash-lite-preview-09-2025",
"name": "Gemini 2.5 Flash Lite Preview 09-2025",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.09999999999999999,
"output": 0.39999999999999997,
"cacheRead": 0.01,
"cacheWrite": 0.08333333333333334
},
"contextWindow": 1048576,
"maxTokens": 65535,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"google/gemini-2.5-flash-preview-09-2025": {
"id": "google/gemini-2.5-flash-preview-09-2025",
"name": "Gemini 2.5 Flash Preview 09-2025",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 2.5,
"cacheRead": 0.03,
"cacheWrite": 0.08333333333333334
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"google/gemini-2.5-pro": {
"id": "google/gemini-2.5-pro",
"name": "Gemini 2.5 Pro",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0.375
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"google/gemini-2.5-pro-preview": {
"id": "google/gemini-2.5-pro-preview",
"name": "Gemini 2.5 Pro Preview 06-05",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0.375
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"google/gemini-2.5-pro-preview-05-06": {
"id": "google/gemini-2.5-pro-preview-05-06",
"name": "Gemini 2.5 Pro Preview 05-06",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0.375
},
"contextWindow": 1048576,
"maxTokens": 65535,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3-flash-preview": {
"id": "google/gemini-3-flash-preview",
"name": "Gemini 3 Flash (Preview)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.5,
"output": 3,
"cacheRead": 0.049999999999999996,
"cacheWrite": 0.08333333333333334
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3-pro-preview": {
"id": "google/gemini-3-pro-preview",
"name": "Gemini 3 Pro Preview",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 12,
"cacheRead": 0.19999999999999998,
"cacheWrite": 0.375
},
"contextWindow": 1048000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3.1-flash-lite": {
"id": "google/gemini-3.1-flash-lite",
"name": "Gemini 3.1 Flash Lite",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 1.5,
"cacheRead": 0.024999999999999998,
"cacheWrite": 0.08333333333333334
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3.1-flash-lite-preview": {
"id": "google/gemini-3.1-flash-lite-preview",
"name": "Gemini 3.1 Flash Lite Preview",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 1.5,
"cacheRead": 0.024999999999999998,
"cacheWrite": 0.08333333333333334
},
"contextWindow": 1048576,
"maxTokens": 65536
},
"google/gemini-3.1-pro-preview": {
"id": "google/gemini-3.1-pro-preview",
"name": "Gemini 3.1 Pro (Preview)",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 12,
"cacheRead": 0.19999999999999998,
"cacheWrite": 0.375
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3.1-pro-preview-customtools": {
"id": "google/gemini-3.1-pro-preview-customtools",
"name": "Gemini 3.1 Pro (Preview Custom Tools)",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 12,
"cacheRead": 0.19999999999999998,
"cacheWrite": 0.375
},
"contextWindow": 1048756,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3.5-flash": {
"id": "google/gemini-3.5-flash",
"name": "Gemini 3.5 Flash",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.5,
"output": 9,
"cacheRead": 0.15,
"cacheWrite": 0.08333333333333334
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"google/gemma-3-12b-it": {
"id": "google/gemma-3-12b-it",
"name": "Gemma 3 12B",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.049999999999999996,
"output": 0.15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384
},
"google/gemma-3-27b-it": {
"id": "google/gemma-3-27b-it",
"name": "Gemma 3 27B",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.08,
"output": 0.16,
"cacheRead": 0.015,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384
},
"google/gemma-3-27b-it:free": {
"id": "google/gemma-3-27b-it:free",
"name": "Gemma 3 27B (free)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192
},
"google/gemma-4-26b-a4b-it": {
"id": "google/gemma-4-26b-a4b-it",
"name": "Gemma 4 26B A4B",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.06,
"output": 0.33,
"cacheRead": 0.04,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"google/gemma-4-26b-a4b-it:free": {
"id": "google/gemma-4-26b-a4b-it:free",
"name": "Gemma 4 26B A4B (free)",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"google/gemma-4-31b-it": {
"id": "google/gemma-4-31b-it",
"name": "Gemma 4 31B",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.12,
"output": 0.35,
"cacheRead": 0.09,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"google/gemma-4-31b-it:free": {
"id": "google/gemma-4-31b-it:free",
"name": "Gemma 4 31B (free)",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"ibm-granite/granite-4.1-8b": {
"id": "ibm-granite/granite-4.1-8b",
"name": "Granite 4.1 8B",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.049999999999999996,
"output": 0.09999999999999999,
"cacheRead": 0.049999999999999996,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072
},
"inception/mercury": {
"id": "inception/mercury",
"name": "Mercury",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.25,
"output": 0.75,
"cacheRead": 0.024999999999999998,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 32000
},
"inception/mercury-2": {
"id": "inception/mercury-2",
"name": "Mercury 2",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.25,
"output": 0.75,
"cacheRead": 0.024999999999999998,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 50000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"inception/mercury-coder": {
"id": "inception/mercury-coder",
"name": "Mercury Coder",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.25,
"output": 0.75,
"cacheRead": 0.024999999999999998,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 32000
},
"inclusionai/ling-2.6-1t": {
"id": "inclusionai/ling-2.6-1t",
"name": "Ling-2.6-1T",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.075,
"output": 0.625,
"cacheRead": 0.015,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768
},
"inclusionai/ling-2.6-1t:free": {
"id": "inclusionai/ling-2.6-1t:free",
"name": "Ling-2.6-1T (free)",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768
},
"inclusionai/ling-2.6-flash": {
"id": "inclusionai/ling-2.6-flash",
"name": "Ling-2.6 Flash",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.01,
"output": 0.03,
"cacheRead": 0.002,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768
},
"inclusionai/ling-2.6-flash:free": {
"id": "inclusionai/ling-2.6-flash:free",
"name": "Ling-2.6-flash (free)",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768
},
"inclusionai/ring-2.6-1t": {
"id": "inclusionai/ring-2.6-1t",
"name": "Ring-2.6-1T",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.075,
"output": 0.625,
"cacheRead": 0.015,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"inclusionai/ring-2.6-1t:free": {
"id": "inclusionai/ring-2.6-1t:free",
"name": "Ring-2.6-1T (free)",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"kwaipilot/kat-coder-pro": {
"id": "kwaipilot/kat-coder-pro",
"name": "KAT-Coder-Pro V1",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.207,
"output": 0.828,
"cacheRead": 0.0414,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 128000
},
"kwaipilot/kat-coder-pro-v2": {
"id": "kwaipilot/kat-coder-pro-v2",
"name": "KAT-Coder-Pro V2",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.06,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 80000
},
"meituan/longcat-flash-chat": {
"id": "meituan/longcat-flash-chat",
"name": "LongCat Flash Chat",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.19999999999999998,
"output": 0.7999999999999999,
"cacheRead": 0.19999999999999998,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072
},
"meta-llama/llama-3-8b-instruct": {
"id": "meta-llama/llama-3-8b-instruct",
"name": "Llama 3 8B Instruct",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.03,
"output": 0.04,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 8192,
"maxTokens": 16384
},
"meta-llama/llama-3.1-405b-instruct": {
"id": "meta-llama/llama-3.1-405b-instruct",
"name": "Llama 3.1 405B Instruct",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 4,
"output": 4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131000,
"maxTokens": null
},
"meta-llama/llama-3.1-70b-instruct": {
"id": "meta-llama/llama-3.1-70b-instruct",
"name": "Llama 3.1 70B Instruct",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.39999999999999997,
"output": 0.39999999999999997,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384
},
"meta-llama/llama-3.1-8b-instruct": {
"id": "meta-llama/llama-3.1-8b-instruct",
"name": "Llama 3.1 8B Instruct",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.02,
"output": 0.03,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384
},
"meta-llama/llama-3.3-70b-instruct": {
"id": "meta-llama/llama-3.3-70b-instruct",
"name": "Llama 3.3 70B Instruct",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.09999999999999999,
"output": 0.32,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384
},
"meta-llama/llama-3.3-70b-instruct:free": {
"id": "meta-llama/llama-3.3-70b-instruct:free",
"name": "Llama 3.3 70B Instruct (free)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384
},
"meta-llama/llama-4-maverick": {
"id": "meta-llama/llama-4-maverick",
"name": "Llama 4 Maverick",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 16384
},
"meta-llama/llama-4-scout": {
"id": "meta-llama/llama-4-scout",
"name": "Llama 4 Scout",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.09999999999999999,
"output": 0.3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 10000000,
"maxTokens": 16384
},
"minimax/minimax-m1": {
"id": "minimax/minimax-m1",
"name": "MiniMax M1",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.39999999999999997,
"output": 2.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 40000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"minimax/minimax-m2": {
"id": "minimax/minimax-m2",
"name": "MiniMax M2",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.255,
"output": 1,
"cacheRead": 0.03,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 196608,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax/minimax-m2.1": {
"id": "minimax/minimax-m2.1",
"name": "MiniMax M2.1",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.29,
"output": 0.95,
"cacheRead": 0.03,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 196608,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax/minimax-m2.5": {
"id": "minimax/minimax-m2.5",
"name": "MiniMax M2.5",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.8999999999999999,
"cacheRead": 0.049999999999999996,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 196608,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax/minimax-m2.5:free": {
"id": "minimax/minimax-m2.5:free",
"name": "MiniMax M2.5 (free)",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
},
"compat": {
"supportsToolChoice": false
}
},
"minimax/minimax-m2.7": {
"id": "minimax/minimax-m2.7",
"name": "MiniMax M2.7",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.25,
"output": 1,
"cacheRead": 0.049999999999999996,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax/minimax-m3": {
"id": "minimax/minimax-m3",
"name": "MiniMax-M3",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.06,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 512000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"mistralai/codestral-2508": {
"id": "mistralai/codestral-2508",
"name": "Codestral 2508",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 0.8999999999999999,
"cacheRead": 0.03,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 51200
},
"mistralai/devstral-2512": {
"id": "mistralai/devstral-2512",
"name": "Devstral 2 2512",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.39999999999999997,
"output": 2,
"cacheRead": 0.04,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"mistralai/devstral-medium": {
"id": "mistralai/devstral-medium",
"name": "Devstral Medium",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.39999999999999997,
"output": 2,
"cacheRead": 0.04,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 26215
},
"mistralai/devstral-small": {
"id": "mistralai/devstral-small",
"name": "Devstral Small 1.1",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.09999999999999999,
"output": 0.3,
"cacheRead": 0.01,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 26215
},
"mistralai/ministral-14b-2512": {
"id": "mistralai/ministral-14b-2512",
"name": "Ministral 3 14B 2512",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.19999999999999998,
"output": 0.19999999999999998,
"cacheRead": 0.02,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 52429
},
"mistralai/ministral-3b-2512": {
"id": "mistralai/ministral-3b-2512",
"name": "Ministral 3 3B 2512",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.09999999999999999,
"output": 0.09999999999999999,
"cacheRead": 0.01,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768
},
"mistralai/ministral-8b-2512": {
"id": "mistralai/ministral-8b-2512",
"name": "Ministral 3 8B 2512",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 0.15,
"cacheRead": 0.015,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768
},
"mistralai/mistral-large": {
"id": "mistralai/mistral-large",
"name": "Mistral Large",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 2,
"output": 6,
"cacheRead": 0.19999999999999998,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 25600
},
"mistralai/mistral-large-2407": {
"id": "mistralai/mistral-large-2407",
"name": "Mistral Large 2407",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 2,
"output": 6,
"cacheRead": 0.19999999999999998,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768
},
"mistralai/mistral-large-2411": {
"id": "mistralai/mistral-large-2411",
"name": "Mistral Large 2411",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 2,
"output": 6,
"cacheRead": 0.19999999999999998,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384
},
"mistralai/mistral-large-2512": {
"id": "mistralai/mistral-large-2512",
"name": "Mistral Large 3 2512",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.5,
"output": 1.5,
"cacheRead": 0.049999999999999996,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"mistralai/mistral-medium-3": {
"id": "mistralai/mistral-medium-3",
"name": "Mistral Medium 3",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.39999999999999997,
"output": 2,
"cacheRead": 0.04,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 26215
},
"mistralai/mistral-medium-3-5": {
"id": "mistralai/mistral-medium-3-5",
"name": "Mistral Medium 3.5",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.5,
"output": 7.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"mistralai/mistral-medium-3.1": {
"id": "mistralai/mistral-medium-3.1",
"name": "Mistral Medium 3.1",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.39999999999999997,
"output": 2,
"cacheRead": 0.04,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 26215
},
"mistralai/mistral-nemo": {
"id": "mistralai/mistral-nemo",
"name": "Mistral Nemo",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.02,
"output": 0.03,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 128000
},
"mistralai/mistral-saba": {
"id": "mistralai/mistral-saba",
"name": "Saba",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.19999999999999998,
"output": 0.6,
"cacheRead": 0.02,
"cacheWrite": 0
},
"contextWindow": 32768,
"maxTokens": 32768
},
"mistralai/mistral-small-24b-instruct-2501": {
"id": "mistralai/mistral-small-24b-instruct-2501",
"name": "Mistral Small 3",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.049999999999999996,
"output": 0.08,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32768,
"maxTokens": 16384
},
"mistralai/mistral-small-2603": {
"id": "mistralai/mistral-small-2603",
"name": "Mistral Small 4",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0.015,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 256000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"mistralai/mistral-small-3.1-24b-instruct": {
"id": "mistralai/mistral-small-3.1-24b-instruct",
"name": "Mistral Small 3.1 24B",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.03,
"output": 0.11,
"cacheRead": 0.015,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072
},
"mistralai/mistral-small-3.1-24b-instruct:free": {
"id": "mistralai/mistral-small-3.1-24b-instruct:free",
"name": "Mistral Small 3.1 24B (free)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": null
},
"mistralai/mistral-small-3.2-24b-instruct": {
"id": "mistralai/mistral-small-3.2-24b-instruct",
"name": "Mistral Small 3.2 24B",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.075,
"output": 0.19999999999999998,
"cacheRead": 0.03,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"mistralai/mistral-small-creative": {
"id": "mistralai/mistral-small-creative",
"name": "Mistral Small Creative",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.09999999999999999,
"output": 0.3,
"cacheRead": 0.01,
"cacheWrite": 0
},
"contextWindow": 32768,
"maxTokens": null
},
"mistralai/mixtral-8x22b-instruct": {
"id": "mistralai/mixtral-8x22b-instruct",
"name": "Mixtral 8x22B Instruct",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 2,
"output": 6,
"cacheRead": 0.19999999999999998,
"cacheWrite": 0
},
"contextWindow": 65536,
"maxTokens": 13108
},
"mistralai/mixtral-8x7b-instruct": {
"id": "mistralai/mixtral-8x7b-instruct",
"name": "Mixtral 8x7B Instruct",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.54,
"output": 0.54,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32768,
"maxTokens": 16384
},
"mistralai/pixtral-large-2411": {
"id": "mistralai/pixtral-large-2411",
"name": "Pixtral Large 2411",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 6,
"cacheRead": 0.19999999999999998,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768
},
"mistralai/voxtral-small-24b-2507": {
"id": "mistralai/voxtral-small-24b-2507",
"name": "Voxtral Small 24B 2507",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.09999999999999999,
"output": 0.3,
"cacheRead": 0.01,
"cacheWrite": 0
},
"contextWindow": 32000,
"maxTokens": 6400
},
"moonshotai/kimi-k2": {
"id": "moonshotai/kimi-k2",
"name": "Kimi K2 0711",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.5700000000000001,
"output": 2.3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768
},
"moonshotai/kimi-k2-0905": {
"id": "moonshotai/kimi-k2-0905",
"name": "Kimi K2 0905",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.5,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"moonshotai/kimi-k2-0905:exacto": {
"id": "moonshotai/kimi-k2-0905:exacto",
"name": "Kimi K2 0905 (exacto)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"moonshotai/kimi-k2-thinking": {
"id": "moonshotai/kimi-k2-thinking",
"name": "Kimi K2 Thinking",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.5,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"moonshotai/kimi-k2.5": {
"id": "moonshotai/kimi-k2.5",
"name": "Kimi K2.5",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.375,
"output": 2.025,
"cacheRead": 0.09,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"moonshotai/kimi-k2.6": {
"id": "moonshotai/kimi-k2.6",
"name": "Kimi K2.6",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.6799999999999999,
"output": 3.41,
"cacheRead": 0.33999999999999997,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262142,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"moonshotai/kimi-k2.6:free": {
"id": "moonshotai/kimi-k2.6:free",
"name": "Kimi K2.6 (free)",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"moonshotai/kimi-k2.7-code": {
"id": "moonshotai/kimi-k2.7-code",
"name": "Kimi K2.7 Code",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.74,
"output": 3.5,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"nex-agi/deepseek-v3.1-nex-n1": {
"id": "nex-agi/deepseek-v3.1-nex-n1",
"name": "DeepSeek V3.1 Nex N1",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.135,
"output": 0.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 163840
},
"nex-agi/nex-n2-pro:free": {
"id": "nex-agi/nex-n2-pro:free",
"name": "Nex-N2-Pro (free)",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"nousresearch/deephermes-3-mistral-24b-preview": {
"id": "nousresearch/deephermes-3-mistral-24b-preview",
"name": "DeepHermes 3 Mistral 24B Preview",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.02,
"output": 0.09999999999999999,
"cacheRead": 0.01,
"cacheWrite": 0
},
"contextWindow": 32768,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"nousresearch/hermes-4-70b": {
"id": "nousresearch/hermes-4-70b",
"name": "Hermes 4 70B",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.11,
"output": 0.38,
"cacheRead": 0.055,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"nvidia/llama-3.1-nemotron-70b-instruct": {
"id": "nvidia/llama-3.1-nemotron-70b-instruct",
"name": "Llama 3.1 Nemotron 70b Instruct",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 1.2,
"output": 1.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384
},
"nvidia/llama-3.3-nemotron-super-49b-v1.5": {
"id": "nvidia/llama-3.3-nemotron-super-49b-v1.5",
"name": "Llama 3.3 Nemotron Super 49B V1.5",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.39999999999999997,
"output": 0.39999999999999997,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"nvidia/nemotron-3-nano-30b-a3b": {
"id": "nvidia/nemotron-3-nano-30b-a3b",
"name": "Nemotron 3 Nano 30B A3B",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.049999999999999996,
"output": 0.19999999999999998,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 228000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"nvidia/nemotron-3-nano-30b-a3b:free": {
"id": "nvidia/nemotron-3-nano-30b-a3b:free",
"name": "Nemotron 3 Nano 30B A3B (free)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": null,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": {
"id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
"name": "Nemotron 3 Nano Omni (free)",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"nvidia/nemotron-3-super-120b-a12b": {
"id": "nvidia/nemotron-3-super-120b-a12b",
"name": "Nemotron 3 Super",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.09,
"output": 0.44999999999999996,
"cacheRead": 0.09999999999999999,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"nvidia/nemotron-3-super-120b-a12b:free": {
"id": "nvidia/nemotron-3-super-120b-a12b:free",
"name": "Nemotron 3 Super (free)",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"nvidia/nemotron-3-ultra-550b-a55b": {
"id": "nvidia/nemotron-3-ultra-550b-a55b",
"name": "Nemotron 3 Ultra 550B A55B",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.5,
"output": 2.2,
"cacheRead": 0.09999999999999999,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"nvidia/nemotron-3-ultra-550b-a55b:free": {
"id": "nvidia/nemotron-3-ultra-550b-a55b:free",
"name": "Nemotron 3 Ultra (free)",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"nvidia/nemotron-nano-12b-v2-vl:free": {
"id": "nvidia/nemotron-nano-12b-v2-vl:free",
"name": "Nemotron Nano 12B 2 VL (free)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"nvidia/nemotron-nano-9b-v2": {
"id": "nvidia/nemotron-nano-9b-v2",
"name": "Nemotron Nano 9B V2",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.04,
"output": 0.16,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"nvidia/nemotron-nano-9b-v2:free": {
"id": "nvidia/nemotron-nano-9b-v2:free",
"name": "Nemotron Nano 9B V2 (free)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": null,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-3.5-turbo": {
"id": "openai/gpt-3.5-turbo",
"name": "GPT-3.5 Turbo",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.5,
"output": 1.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 16385,
"maxTokens": 4096
},
"openai/gpt-3.5-turbo-0613": {
"id": "openai/gpt-3.5-turbo-0613",
"name": "GPT-3.5 Turbo (older v0613)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 4095,
"maxTokens": 4096
},
"openai/gpt-3.5-turbo-16k": {
"id": "openai/gpt-3.5-turbo-16k",
"name": "GPT-3.5 Turbo 16k",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 3,
"output": 4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 16385,
"maxTokens": 4096
},
"openai/gpt-4": {
"id": "openai/gpt-4",
"name": "GPT-4",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 30,
"output": 60,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 8191,
"maxTokens": 8192
},
"openai/gpt-4-0314": {
"id": "openai/gpt-4-0314",
"name": "GPT-4 (older v0314)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 30,
"output": 60,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 8191,
"maxTokens": 4096
},
"openai/gpt-4-1106-preview": {
"id": "openai/gpt-4-1106-preview",
"name": "GPT-4 Turbo (older v1106)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 10,
"output": 30,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"openai/gpt-4-turbo": {
"id": "openai/gpt-4-turbo",
"name": "GPT-4 Turbo",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 10,
"output": 30,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"openai/gpt-4-turbo-preview": {
"id": "openai/gpt-4-turbo-preview",
"name": "GPT-4 Turbo Preview",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 10,
"output": 30,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"openai/gpt-4.1": {
"id": "openai/gpt-4.1",
"name": "GPT-4.1",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 8,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 1047576,
"maxTokens": 32768
},
"openai/gpt-4.1-mini": {
"id": "openai/gpt-4.1-mini",
"name": "GPT-4.1 Mini",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.39999999999999997,
"output": 1.5999999999999999,
"cacheRead": 0.09999999999999999,
"cacheWrite": 0
},
"contextWindow": 1047576,
"maxTokens": 32768
},
"openai/gpt-4.1-nano": {
"id": "openai/gpt-4.1-nano",
"name": "GPT-4.1 Nano",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.09999999999999999,
"output": 0.39999999999999997,
"cacheRead": 0.024999999999999998,
"cacheWrite": 0
},
"contextWindow": 1047576,
"maxTokens": 32768
},
"openai/gpt-4o": {
"id": "openai/gpt-4o",
"name": "GPT-4o",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 10,
"cacheRead": 1.25,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-4o-2024-05-13": {
"id": "openai/gpt-4o-2024-05-13",
"name": "GPT-4o (2024-05-13)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"openai/gpt-4o-2024-08-06": {
"id": "openai/gpt-4o-2024-08-06",
"name": "GPT-4o (2024-08-06)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 10,
"cacheRead": 1.25,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-4o-2024-11-20": {
"id": "openai/gpt-4o-2024-11-20",
"name": "GPT-4o (2024-11-20)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 10,
"cacheRead": 1.25,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-4o-audio-preview": {
"id": "openai/gpt-4o-audio-preview",
"name": "GPT-4o Audio",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 2.5,
"output": 10,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-4o-mini": {
"id": "openai/gpt-4o-mini",
"name": "GPT-4o mini",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0.075,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-4o-mini-2024-07-18": {
"id": "openai/gpt-4o-mini-2024-07-18",
"name": "GPT-4o-mini (2024-07-18)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0.075,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-4o:extended": {
"id": "openai/gpt-4o:extended",
"name": "GPT-4o (extended)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 6,
"output": 18,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 64000
},
"openai/gpt-5": {
"id": "openai/gpt-5",
"name": "GPT-5",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5-codex": {
"id": "openai/gpt-5-codex",
"name": "GPT-5 Codex",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5-image": {
"id": "openai/gpt-5-image",
"name": "GPT-5 Image",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 10,
"output": 10,
"cacheRead": 1.25,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5-image-mini": {
"id": "openai/gpt-5-image-mini",
"name": "GPT-5 Image Mini",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 2,
"cacheRead": 0.25,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5-mini": {
"id": "openai/gpt-5-mini",
"name": "GPT-5 Mini",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 2,
"cacheRead": 0.024999999999999998,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5-nano": {
"id": "openai/gpt-5-nano",
"name": "GPT-5 Nano",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.049999999999999996,
"output": 0.39999999999999997,
"cacheRead": 0.01,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5-pro": {
"id": "openai/gpt-5-pro",
"name": "GPT-5 Pro",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 120,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5.1": {
"id": "openai/gpt-5.1",
"name": "GPT-5.1",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.13,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5.1-chat": {
"id": "openai/gpt-5.1-chat",
"name": "GPT-5.1 Chat",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.13,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 32000
},
"openai/gpt-5.1-codex": {
"id": "openai/gpt-5.1-codex",
"name": "GPT-5.1 Codex",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.13,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5.1-codex-max": {
"id": "openai/gpt-5.1-codex-max",
"name": "GPT-5.1-Codex-Max",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5.1-codex-mini": {
"id": "openai/gpt-5.1-codex-mini",
"name": "GPT-5.1-Codex-Mini",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 2,
"cacheRead": 0.024999999999999998,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"medium",
"high"
]
}
},
"openai/gpt-5.2": {
"id": "openai/gpt-5.2",
"name": "GPT-5.2",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.2-chat": {
"id": "openai/gpt-5.2-chat",
"name": "GPT-5.2 Chat",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-5.2-codex": {
"id": "openai/gpt-5.2-codex",
"name": "GPT-5.2 Codex",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.2-pro": {
"id": "openai/gpt-5.2-pro",
"name": "GPT-5.2 Pro",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 21,
"output": 168,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.3-chat": {
"id": "openai/gpt-5.3-chat",
"name": "GPT-5.3 Chat",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-5.3-codex": {
"id": "openai/gpt-5.3-codex",
"name": "GPT-5.3 Codex",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.4": {
"id": "openai/gpt-5.4",
"name": "GPT-5.4",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 15,
"cacheRead": 0.25,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.4-mini": {
"id": "openai/gpt-5.4-mini",
"name": "GPT-5.4 Mini",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.75,
"output": 4.5,
"cacheRead": 0.075,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.4-nano": {
"id": "openai/gpt-5.4-nano",
"name": "GPT-5.4 Nano",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.19999999999999998,
"output": 1.25,
"cacheRead": 0.02,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.4-pro": {
"id": "openai/gpt-5.4-pro",
"name": "GPT-5.4 Pro",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 30,
"output": 180,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.5": {
"id": "openai/gpt-5.5",
"name": "GPT-5.5",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 30,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
},
"contextPromotionTarget": "openrouter/openai/gpt-5.4"
},
"openai/gpt-5.5-pro": {
"id": "openai/gpt-5.5-pro",
"name": "GPT-5.5 Pro",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 30,
"output": 180,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
},
"contextPromotionTarget": "openrouter/openai/gpt-5.4"
},
"openai/gpt-audio": {
"id": "openai/gpt-audio",
"name": "GPT Audio",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 2.5,
"output": 10,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-audio-mini": {
"id": "openai/gpt-audio-mini",
"name": "GPT Audio Mini",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-chat-latest": {
"id": "openai/gpt-chat-latest",
"name": "GPT Chat Latest",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 30,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-oss-120b": {
"id": "openai/gpt-oss-120b",
"name": "GPT OSS 120B",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.039,
"output": 0.18,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
]
}
},
"openai/gpt-oss-120b:exacto": {
"id": "openai/gpt-oss-120b:exacto",
"name": "gpt-oss-120b (exacto)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.039,
"output": 0.19,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 40960,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
]
}
},
"openai/gpt-oss-120b:free": {
"id": "openai/gpt-oss-120b:free",
"name": "gpt-oss-120b (free)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
]
}
},
"openai/gpt-oss-20b": {
"id": "openai/gpt-oss-20b",
"name": "GPT OSS 20B",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.029,
"output": 0.14,
"cacheRead": 0.015,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
]
}
},
"openai/gpt-oss-20b:free": {
"id": "openai/gpt-oss-20b:free",
"name": "gpt-oss-20b (free)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
]
}
},
"openai/gpt-oss-safeguard-20b": {
"id": "openai/gpt-oss-safeguard-20b",
"name": "Safety GPT OSS 20B",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.075,
"output": 0.3,
"cacheRead": 0.037,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
]
}
},
"openai/o1": {
"id": "openai/o1",
"name": "o1",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 60,
"cacheRead": 7.5,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"openai/o3": {
"id": "openai/o3",
"name": "o3",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 8,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"openai/o3-deep-research": {
"id": "openai/o3-deep-research",
"name": "o3 Deep Research",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 10,
"output": 40,
"cacheRead": 2.5,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"openai/o3-mini": {
"id": "openai/o3-mini",
"name": "o3-mini",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.1,
"output": 4.4,
"cacheRead": 0.55,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"openai/o3-mini-high": {
"id": "openai/o3-mini-high",
"name": "o3 Mini High",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 1.1,
"output": 4.4,
"cacheRead": 0.55,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000
},
"openai/o3-pro": {
"id": "openai/o3-pro",
"name": "o3-pro",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 20,
"output": 80,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"openai/o4-mini": {
"id": "openai/o4-mini",
"name": "o4-mini",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.1,
"output": 4.4,
"cacheRead": 0.275,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"openai/o4-mini-deep-research": {
"id": "openai/o4-mini-deep-research",
"name": "o4 Mini Deep Research",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 8,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"openai/o4-mini-high": {
"id": "openai/o4-mini-high",
"name": "o4 Mini High",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.1,
"output": 4.4,
"cacheRead": 0.275,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"openrouter/aurora-alpha": {
"id": "openrouter/aurora-alpha",
"name": "Aurora Alpha",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 50000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openrouter/auto": {
"id": "openrouter/auto",
"name": "Auto Router",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": -1000000,
"output": -1000000,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 30000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openrouter/elephant-alpha": {
"id": "openrouter/elephant-alpha",
"name": "Elephant",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768
},
"openrouter/free": {
"id": "openrouter/free",
"name": "Free Models Router",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openrouter/healer-alpha": {
"id": "openrouter/healer-alpha",
"name": "Healer Alpha",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openrouter/hunter-alpha": {
"id": "openrouter/hunter-alpha",
"name": "Hunter Alpha",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openrouter/owl-alpha": {
"id": "openrouter/owl-alpha",
"name": "Owl Alpha",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048756,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
},
"compat": {
"supportsToolChoice": false
}
},
"poolside/laguna-m.1:free": {
"id": "poolside/laguna-m.1:free",
"name": "Laguna M.1 (free)",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"poolside/laguna-xs.2:free": {
"id": "poolside/laguna-xs.2:free",
"name": "Laguna XS.2 (free)",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"prime-intellect/intellect-3": {
"id": "prime-intellect/intellect-3",
"name": "INTELLECT-3",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.19999999999999998,
"output": 1.1,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen-2.5-72b-instruct": {
"id": "qwen/qwen-2.5-72b-instruct",
"name": "Qwen2.5 72B Instruct",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.36,
"output": 0.39999999999999997,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384
},
"qwen/qwen-2.5-7b-instruct": {
"id": "qwen/qwen-2.5-7b-instruct",
"name": "Qwen2.5 7B Instruct",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.04,
"output": 0.09999999999999999,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768
},
"qwen/qwen-max": {
"id": "qwen/qwen-max",
"name": "Qwen-Max",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 1.04,
"output": 4.16,
"cacheRead": 0.20800000000000002,
"cacheWrite": 0
},
"contextWindow": 32768,
"maxTokens": 8192
},
"qwen/qwen-plus": {
"id": "qwen/qwen-plus",
"name": "Qwen-Plus",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.26,
"output": 0.78,
"cacheRead": 0.052000000000000005,
"cacheWrite": 0.325
},
"contextWindow": 1000000,
"maxTokens": 32768
},
"qwen/qwen-plus-2025-07-28": {
"id": "qwen/qwen-plus-2025-07-28",
"name": "Qwen Plus 0728",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.26,
"output": 0.78,
"cacheRead": 0,
"cacheWrite": 0.325
},
"contextWindow": 1000000,
"maxTokens": 32768
},
"qwen/qwen-plus-2025-07-28:thinking": {
"id": "qwen/qwen-plus-2025-07-28:thinking",
"name": "Qwen Plus 0728 (thinking)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.26,
"output": 0.78,
"cacheRead": 0,
"cacheWrite": 0.325
},
"contextWindow": 1000000,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen-turbo": {
"id": "qwen/qwen-turbo",
"name": "Qwen-Turbo",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.0325,
"output": 0.13,
"cacheRead": 0.006500000000000001,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192
},
"qwen/qwen-vl-max": {
"id": "qwen/qwen-vl-max",
"name": "Qwen VL Max",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.52,
"output": 2.08,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768
},
"qwen/qwen3-14b": {
"id": "qwen/qwen3-14b",
"name": "Qwen3 14B",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.09999999999999999,
"output": 0.24,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131702,
"maxTokens": 40960,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3-235b-a22b": {
"id": "qwen/qwen3-235b-a22b",
"name": "Qwen3 235B A22B",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.45499999999999996,
"output": 1.8199999999999998,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3-235b-a22b-2507": {
"id": "qwen/qwen3-235b-a22b-2507",
"name": "Qwen3 235B A22B Instruct 2507",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.09,
"output": 0.09999999999999999,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3-235b-a22b-thinking-2507": {
"id": "qwen/qwen3-235b-a22b-thinking-2507",
"name": "Qwen3 235B A22B Thinking 2507",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.09999999999999999,
"output": 0.09999999999999999,
"cacheRead": 0.09999999999999999,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"qwen/qwen3-30b-a3b": {
"id": "qwen/qwen3-30b-a3b",
"name": "Qwen3 30B A3B",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.12,
"output": 0.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3-30b-a3b-instruct-2507": {
"id": "qwen/qwen3-30b-a3b-instruct-2507",
"name": "Qwen3 30B A3B Instruct 2507",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.04815,
"output": 0.19305,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32000
},
"qwen/qwen3-30b-a3b-thinking-2507": {
"id": "qwen/qwen3-30b-a3b-thinking-2507",
"name": "Qwen3 30B A3B Thinking 2507",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.08,
"output": 0.39999999999999997,
"cacheRead": 0.08,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"qwen/qwen3-32b": {
"id": "qwen/qwen3-32b",
"name": "Qwen3-32B",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.08,
"output": 0.28,
"cacheRead": 0.04,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3-4b": {
"id": "qwen/qwen3-4b",
"name": "Qwen3 4B",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.0715,
"output": 0.273,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3-4b:free": {
"id": "qwen/qwen3-4b:free",
"name": "Qwen3 4B (free)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 40960,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3-8b": {
"id": "qwen/qwen3-8b",
"name": "Qwen3 8B",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.049999999999999996,
"output": 0.39999999999999997,
"cacheRead": 0.049999999999999996,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3-coder": {
"id": "qwen/qwen3-coder",
"name": "Qwen3 Coder 480B A35B",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.22,
"output": 1.7999999999999998,
"cacheRead": 0.022,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536
},
"qwen/qwen3-coder-30b-a3b-instruct": {
"id": "qwen/qwen3-coder-30b-a3b-instruct",
"name": "Qwen3 Coder 30B A3B Instruct",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.07,
"output": 0.27,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 160000,
"maxTokens": 32768
},
"qwen/qwen3-coder-flash": {
"id": "qwen/qwen3-coder-flash",
"name": "Qwen3 Coder Flash",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.195,
"output": 0.975,
"cacheRead": 0.039,
"cacheWrite": 0.24375
},
"contextWindow": 1000000,
"maxTokens": 65536
},
"qwen/qwen3-coder-next": {
"id": "qwen/qwen3-coder-next",
"name": "Qwen3 Coder Next",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.11,
"output": 0.7999999999999999,
"cacheRead": 0.07,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"qwen/qwen3-coder-plus": {
"id": "qwen/qwen3-coder-plus",
"name": "Qwen3 Coder Plus",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.65,
"output": 3.25,
"cacheRead": 0.13,
"cacheWrite": 0.8125
},
"contextWindow": 1000000,
"maxTokens": 65536
},
"qwen/qwen3-coder:exacto": {
"id": "qwen/qwen3-coder:exacto",
"name": "Qwen3 Coder 480B A35B (exacto)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.22,
"output": 1.7999999999999998,
"cacheRead": 0.022,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536
},
"qwen/qwen3-coder:free": {
"id": "qwen/qwen3-coder:free",
"name": "Qwen3 Coder 480B A35B (free)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 262000
},
"qwen/qwen3-max": {
"id": "qwen/qwen3-max",
"name": "Qwen3 Max",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.78,
"output": 3.9,
"cacheRead": 0.156,
"cacheWrite": 0.975
},
"contextWindow": 262144,
"maxTokens": 32768
},
"qwen/qwen3-max-thinking": {
"id": "qwen/qwen3-max-thinking",
"name": "Qwen3 Max Thinking",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.78,
"output": 3.9,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"qwen/qwen3-next-80b-a3b-instruct": {
"id": "qwen/qwen3-next-80b-a3b-instruct",
"name": "Qwen3-Next-80B-A3B-Instruct",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.09,
"output": 1.1,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 16384
},
"qwen/qwen3-next-80b-a3b-instruct:free": {
"id": "qwen/qwen3-next-80b-a3b-instruct:free",
"name": "Qwen3 Next 80B A3B Instruct (free)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 16384
},
"qwen/qwen3-next-80b-a3b-thinking": {
"id": "qwen/qwen3-next-80b-a3b-thinking",
"name": "Qwen3 Next 80B A3B Thinking",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.0975,
"output": 0.78,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"qwen/qwen3-vl-235b-a22b-instruct": {
"id": "qwen/qwen3-vl-235b-a22b-instruct",
"name": "Qwen3 VL 235B A22B Instruct",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.19999999999999998,
"output": 0.88,
"cacheRead": 0.11,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 16384
},
"qwen/qwen3-vl-235b-a22b-thinking": {
"id": "qwen/qwen3-vl-235b-a22b-thinking",
"name": "Qwen3 VL 235B A22B Thinking",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.26,
"output": 2.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"qwen/qwen3-vl-30b-a3b-instruct": {
"id": "qwen/qwen3-vl-30b-a3b-instruct",
"name": "Qwen3 VL 30B A3B Instruct",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.13,
"output": 0.52,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768
},
"qwen/qwen3-vl-30b-a3b-thinking": {
"id": "qwen/qwen3-vl-30b-a3b-thinking",
"name": "Qwen3 VL 30B A3B Thinking",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.13,
"output": 1.56,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"qwen/qwen3-vl-32b-instruct": {
"id": "qwen/qwen3-vl-32b-instruct",
"name": "Qwen3 VL 32B Instruct",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.10400000000000001,
"output": 0.41600000000000004,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768
},
"qwen/qwen3-vl-8b-instruct": {
"id": "qwen/qwen3-vl-8b-instruct",
"name": "Qwen3 VL 8B Instruct",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.08,
"output": 0.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 32768
},
"qwen/qwen3-vl-8b-thinking": {
"id": "qwen/qwen3-vl-8b-thinking",
"name": "Qwen3 VL 8B Thinking",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.117,
"output": 1.365,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"qwen/qwen3.5-122b-a10b": {
"id": "qwen/qwen3.5-122b-a10b",
"name": "Qwen3.5 122B-A10B",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.26,
"output": 2.08,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.5-27b": {
"id": "qwen/qwen3.5-27b",
"name": "Qwen3.5-27B",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.195,
"output": 1.56,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.5-35b-a3b": {
"id": "qwen/qwen3.5-35b-a3b",
"name": "Qwen3.5-35B-A3B",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.14,
"output": 1,
"cacheRead": 0.049999999999999996,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 81920,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.5-397b-a17b": {
"id": "qwen/qwen3.5-397b-a17b",
"name": "Qwen3.5 397B A17B",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.385,
"output": 2.4499999999999997,
"cacheRead": 0.195,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.5-9b": {
"id": "qwen/qwen3.5-9b",
"name": "Qwen3.5-9B",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.09999999999999999,
"output": 0.15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.5-flash-02-23": {
"id": "qwen/qwen3.5-flash-02-23",
"name": "Qwen3.5-Flash",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.065,
"output": 0.26,
"cacheRead": 0,
"cacheWrite": 0.08125
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.5-plus-02-15": {
"id": "qwen/qwen3.5-plus-02-15",
"name": "Qwen3.5 Plus 2026-02-15",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.26,
"output": 1.56,
"cacheRead": 0,
"cacheWrite": 0.325
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.5-plus-20260420": {
"id": "qwen/qwen3.5-plus-20260420",
"name": "Qwen3.5 Plus 2026-04-20",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 1.7999999999999998,
"cacheRead": 0,
"cacheWrite": 0.375
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.6-27b": {
"id": "qwen/qwen3.6-27b",
"name": "Qwen3.6 27B",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.28850000000000003,
"output": 3.17,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262140,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.6-35b-a3b": {
"id": "qwen/qwen3.6-35b-a3b",
"name": "Qwen3.6 35B A3B",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 1,
"cacheRead": 0.049999999999999996,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.6-flash": {
"id": "qwen/qwen3.6-flash",
"name": "Qwen3.6 Flash",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1875,
"output": 1.125,
"cacheRead": 0,
"cacheWrite": 0.234375
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.6-max-preview": {
"id": "qwen/qwen3.6-max-preview",
"name": "Qwen3.6 Max Preview",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.04,
"output": 6.24,
"cacheRead": 0,
"cacheWrite": 1.3
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.6-plus": {
"id": "qwen/qwen3.6-plus",
"name": "Qwen3.6 Plus",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.325,
"output": 1.95,
"cacheRead": 0,
"cacheWrite": 0.40625
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.6-plus-preview:free": {
"id": "qwen/qwen3.6-plus-preview:free",
"name": "Qwen3.6 Plus Preview (free)",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.6-plus:free": {
"id": "qwen/qwen3.6-plus:free",
"name": "Qwen3.6 Plus (free)",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.7-max": {
"id": "qwen/qwen3.7-max",
"name": "Qwen3.7 Max",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.25,
"output": 3.75,
"cacheRead": 0.25,
"cacheWrite": 1.5625
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.7-plus": {
"id": "qwen/qwen3.7-plus",
"name": "Qwen3.7 Plus",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.32,
"output": 1.28,
"cacheRead": 0.064,
"cacheWrite": 0.39999999999999997
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwq-32b": {
"id": "qwen/qwq-32b",
"name": "QwQ 32B",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.58,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"reka/reka-edge": {
"id": "reka/reka-edge",
"name": "Reka Edge",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.09999999999999999,
"output": 0.09999999999999999,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 16384,
"maxTokens": 16384
},
"rekaai/reka-edge": {
"id": "rekaai/reka-edge",
"name": "Reka Edge",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.09999999999999999,
"output": 0.09999999999999999,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 16384,
"maxTokens": 16384
},
"relace/relace-search": {
"id": "relace/relace-search",
"name": "Relace Search",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 128000
},
"sao10k/l3-euryale-70b": {
"id": "sao10k/l3-euryale-70b",
"name": "Llama 3 Euryale 70B v2.1",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 1.48,
"output": 1.48,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 8192,
"maxTokens": 8192
},
"sao10k/l3.1-euryale-70b": {
"id": "sao10k/l3.1-euryale-70b",
"name": "Llama 3.1 Euryale 70B v2.2",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.85,
"output": 0.85,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 16384
},
"stepfun/step-3.5-flash": {
"id": "stepfun/step-3.5-flash",
"name": "Step 3.5 Flash",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.09,
"output": 0.3,
"cacheRead": 0.02,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
},
"compat": {
"supportsToolChoice": false
}
},
"stepfun/step-3.5-flash:free": {
"id": "stepfun/step-3.5-flash:free",
"name": "Step 3.5 Flash (free)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
},
"compat": {
"supportsToolChoice": false
}
},
"stepfun/step-3.7-flash": {
"id": "stepfun/step-3.7-flash",
"name": "Step 3.7 Flash",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.19999999999999998,
"output": 1.15,
"cacheRead": 0.04,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
},
"compat": {
"supportsToolChoice": false
}
},
"tencent/hy3-preview": {
"id": "tencent/hy3-preview",
"name": "Hy3 Preview",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.06599999999999999,
"output": 0.26,
"cacheRead": 0.029,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"tencent/hy3-preview:free": {
"id": "tencent/hy3-preview:free",
"name": "Hy3 preview (free)",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"thedrummer/rocinante-12b": {
"id": "thedrummer/rocinante-12b",
"name": "Rocinante 12B",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.16999999999999998,
"output": 0.43,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32768,
"maxTokens": 32768
},
"thedrummer/unslopnemo-12b": {
"id": "thedrummer/unslopnemo-12b",
"name": "UnslopNemo 12B",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.39999999999999997,
"output": 0.39999999999999997,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32768,
"maxTokens": 32768
},
"tngtech/deepseek-r1t2-chimera": {
"id": "tngtech/deepseek-r1t2-chimera",
"name": "DeepSeek R1T2 Chimera",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.1,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 163840,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high"
}
}
},
"tngtech/tng-r1t-chimera": {
"id": "tngtech/tng-r1t-chimera",
"name": "R1T Chimera",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.25,
"output": 0.85,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"upstage/solar-pro-3": {
"id": "upstage/solar-pro-3",
"name": "Solar Pro 3",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0.015,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"upstage/solar-pro-3:free": {
"id": "upstage/solar-pro-3:free",
"name": "Solar Pro 3 (free)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"x-ai/grok-3": {
"id": "x-ai/grok-3",
"name": "Grok 3",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.75,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192
},
"x-ai/grok-3-beta": {
"id": "x-ai/grok-3-beta",
"name": "Grok 3 Beta",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.75,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": null
},
"x-ai/grok-3-mini": {
"id": "x-ai/grok-3-mini",
"name": "Grok 3 Mini",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 0.5,
"cacheRead": 0.075,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"x-ai/grok-3-mini-beta": {
"id": "x-ai/grok-3-mini-beta",
"name": "Grok 3 Mini Beta",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 0.5,
"cacheRead": 0.075,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": null,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"x-ai/grok-4": {
"id": "x-ai/grok-4",
"name": "Grok 4",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.75,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"x-ai/grok-4-fast": {
"id": "x-ai/grok-4-fast",
"name": "Grok 4 Fast",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.19999999999999998,
"output": 0.5,
"cacheRead": 0.049999999999999996,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 30000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"x-ai/grok-4.1-fast": {
"id": "x-ai/grok-4.1-fast",
"name": "Grok 4.1 Fast",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.19999999999999998,
"output": 0.5,
"cacheRead": 0.049999999999999996,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 30000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"x-ai/grok-4.20": {
"id": "x-ai/grok-4.20",
"name": "Grok 4.20",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 2.5,
"cacheRead": 0.19999999999999998,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 2000000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"x-ai/grok-4.20-beta": {
"id": "x-ai/grok-4.20-beta",
"name": "Grok 4.20 Beta",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 6,
"cacheRead": 0.19999999999999998,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": null,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"x-ai/grok-4.3": {
"id": "x-ai/grok-4.3",
"name": "Grok 4.3",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 2.5,
"cacheRead": 0.19999999999999998,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 1000000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"x-ai/grok-build-0.1": {
"id": "x-ai/grok-build-0.1",
"name": "Grok Build 0.1",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1,
"output": 2,
"cacheRead": 0.19999999999999998,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"x-ai/grok-code-fast-1": {
"id": "x-ai/grok-code-fast-1",
"name": "Grok Code Fast 1",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.19999999999999998,
"output": 1.5,
"cacheRead": 0.02,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 10000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"xiaomi/mimo-v2-flash": {
"id": "xiaomi/mimo-v2-flash",
"name": "MiMo-V2-Flash",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.09999999999999999,
"output": 0.3,
"cacheRead": 0.01,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"xiaomi/mimo-v2-omni": {
"id": "xiaomi/mimo-v2-omni",
"name": "MiMo V2 Omni",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.39999999999999997,
"output": 2,
"cacheRead": 0.08,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"xiaomi/mimo-v2-pro": {
"id": "xiaomi/mimo-v2-pro",
"name": "MiMo-V2-Pro",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 3,
"cacheRead": 0.19999999999999998,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"xiaomi/mimo-v2.5": {
"id": "xiaomi/mimo-v2.5",
"name": "MiMo-V2.5",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.14,
"output": 0.28,
"cacheRead": 0.0028,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"xiaomi/mimo-v2.5-pro": {
"id": "xiaomi/mimo-v2.5-pro",
"name": "MiMo V2.5 Pro",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.435,
"output": 0.87,
"cacheRead": 0.0036,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"z-ai/glm-4-32b": {
"id": "z-ai/glm-4-32b",
"name": "GLM 4 32B",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.09999999999999999,
"output": 0.09999999999999999,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 32768
},
"z-ai/glm-4.5": {
"id": "z-ai/glm-4.5",
"name": "GLM 4.5",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.2,
"cacheRead": 0.11,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 98304,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"z-ai/glm-4.5-air": {
"id": "z-ai/glm-4.5-air",
"name": "GLM 4.5 Air",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.13,
"output": 0.85,
"cacheRead": 0.024999999999999998,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 98304,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"z-ai/glm-4.5-air:free": {
"id": "z-ai/glm-4.5-air:free",
"name": "GLM 4.5 Air (free)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 96000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"z-ai/glm-4.5v": {
"id": "z-ai/glm-4.5v",
"name": "GLM 4.5V",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.6,
"output": 1.7999999999999998,
"cacheRead": 0.11,
"cacheWrite": 0
},
"contextWindow": 65536,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"z-ai/glm-4.6": {
"id": "z-ai/glm-4.6",
"name": "GLM 4.6",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.43,
"output": 1.74,
"cacheRead": 0.08,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"z-ai/glm-4.6:exacto": {
"id": "z-ai/glm-4.6:exacto",
"name": "GLM 4.6 (exacto)",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.44,
"output": 1.76,
"cacheRead": 0.11,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"z-ai/glm-4.6v": {
"id": "z-ai/glm-4.6v",
"name": "GLM 4.6V",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 0.8999999999999999,
"cacheRead": 0.055,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"z-ai/glm-4.7": {
"id": "z-ai/glm-4.7",
"name": "GLM 4.7",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.39999999999999997,
"output": 1.75,
"cacheRead": 0.08,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"z-ai/glm-4.7-flash": {
"id": "z-ai/glm-4.7-flash",
"name": "GLM 4.7 Flash",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.06,
"output": 0.39999999999999997,
"cacheRead": 0.01,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"z-ai/glm-5": {
"id": "z-ai/glm-5",
"name": "GLM 5",
"api": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 1.92,
"cacheRead": 0.12,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"z-ai/glm-5-turbo": {
"id": "z-ai/glm-5-turbo",
"name": "GLM 5 Turbo",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 1.2,
"output": 4,
"cacheRead": 0.24,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 131072
},
"z-ai/glm-5.1": {
"id": "z-ai/glm-5.1",
"name": "GLM 5.1",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.98,
"output": 3.08,
"cacheRead": 0.182,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"z-ai/glm-5.2": {
"id": "z-ai/glm-5.2",
"name": "GLM 5.2",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.4,
"output": 4.4,
"cacheRead": 0.26,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"z-ai/glm-5v-turbo": {
"id": "z-ai/glm-5v-turbo",
"name": "GLM 5V Turbo",
"api": "openrouter",
"provider": "openrouter",
"baseUrl": "https://openrouter.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 1.2,
"output": 4,
"cacheRead": 0.24,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 131072
}
},
"qianfan": {
"deepseek-v3.2": {
"id": "deepseek-v3.2",
"name": "deepseek-v3.2",
"api": "openai-completions",
"provider": "qianfan",
"baseUrl": "https://qianfan.baidubce.com/v2",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 98304,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
}
},
"qwen-portal": {
"coder-model": {
"id": "coder-model",
"name": "Qwen Coder",
"api": "openai-completions",
"provider": "qwen-portal",
"baseUrl": "https://portal.qwen.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"vision-model": {
"id": "vision-model",
"name": "Qwen Vision",
"api": "openai-completions",
"provider": "qwen-portal",
"baseUrl": "https://portal.qwen.ai/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
}
},
"synthetic": {
"hf:MiniMaxAI/MiniMax-M3": {
"id": "hf:MiniMaxAI/MiniMax-M3",
"name": "MiniMaxAI/MiniMax-M3",
"api": "openai-completions",
"provider": "synthetic",
"baseUrl": "https://api.synthetic.new/openai/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.6,
"output": 1.2,
"cacheRead": 0.6,
"cacheWrite": 0
},
"contextWindow": 524288,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"hf:moonshotai/Kimi-K2.6": {
"id": "hf:moonshotai/Kimi-K2.6",
"name": "moonshotai/Kimi-K2.6",
"api": "openai-completions",
"provider": "synthetic",
"baseUrl": "https://api.synthetic.new/openai/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.95,
"output": 4,
"cacheRead": 0.95,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4": {
"id": "hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4",
"name": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4",
"api": "openai-completions",
"provider": "synthetic",
"baseUrl": "https://api.synthetic.new/openai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1,
"cacheRead": 0.3,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"hf:openai/gpt-oss-120b": {
"id": "hf:openai/gpt-oss-120b",
"name": "openai/gpt-oss-120b",
"api": "openai-completions",
"provider": "synthetic",
"baseUrl": "https://api.synthetic.new/openai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.1,
"output": 0.1,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
]
}
},
"hf:Qwen/Qwen3.5-397B-A17B": {
"id": "hf:Qwen/Qwen3.5-397B-A17B",
"name": "Qwen/Qwen3.5-397B-A17B",
"api": "openai-completions",
"provider": "synthetic",
"baseUrl": "https://api.synthetic.new/openai/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.6,
"output": 3,
"cacheRead": 0.6,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"hf:Qwen/Qwen3.6-27B": {
"id": "hf:Qwen/Qwen3.6-27B",
"name": "Qwen/Qwen3.6-27B",
"api": "openai-completions",
"provider": "synthetic",
"baseUrl": "https://api.synthetic.new/openai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 8192
},
"hf:zai-org/GLM-4.7": {
"id": "hf:zai-org/GLM-4.7",
"name": "zai-org/GLM-4.7",
"api": "openai-completions",
"provider": "synthetic",
"baseUrl": "https://api.synthetic.new/openai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.55,
"output": 2.19,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"hf:zai-org/GLM-4.7-Flash": {
"id": "hf:zai-org/GLM-4.7-Flash",
"name": "zai-org/GLM-4.7-Flash",
"api": "openai-completions",
"provider": "synthetic",
"baseUrl": "https://api.synthetic.new/openai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.06,
"output": 0.4,
"cacheRead": 0.06,
"cacheWrite": 0
},
"contextWindow": 196608,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"hf:zai-org/GLM-5.1": {
"id": "hf:zai-org/GLM-5.1",
"name": "zai-org/GLM-5.1",
"api": "openai-completions",
"provider": "synthetic",
"baseUrl": "https://api.synthetic.new/openai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 3,
"cacheRead": 1,
"cacheWrite": 0
},
"contextWindow": 196608,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"syn:large:text": {
"id": "syn:large:text",
"name": "syn:large:text",
"api": "openai-completions",
"provider": "synthetic",
"baseUrl": "https://api.synthetic.new/openai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 196608,
"maxTokens": 8192
},
"syn:large:vision": {
"id": "syn:large:vision",
"name": "syn:large:vision",
"api": "openai-completions",
"provider": "synthetic",
"baseUrl": "https://api.synthetic.new/openai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 8192
},
"syn:small:text": {
"id": "syn:small:text",
"name": "syn:small:text",
"api": "openai-completions",
"provider": "synthetic",
"baseUrl": "https://api.synthetic.new/openai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 196608,
"maxTokens": 8192
},
"syn:small:vision": {
"id": "syn:small:vision",
"name": "syn:small:vision",
"api": "openai-completions",
"provider": "synthetic",
"baseUrl": "https://api.synthetic.new/openai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 8192
}
},
"together": {
"deepseek-ai/DeepSeek-R1": {
"id": "deepseek-ai/DeepSeek-R1",
"name": "DeepSeek R1",
"api": "openai-completions",
"provider": "together",
"baseUrl": "https://api.together.xyz/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 3,
"output": 7,
"cacheRead": 3,
"cacheWrite": 3
},
"contextWindow": 131072,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek-ai/DeepSeek-V3": {
"id": "deepseek-ai/DeepSeek-V3",
"name": "DeepSeek-V3",
"api": "openai-completions",
"provider": "together",
"baseUrl": "https://api.together.xyz/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 1.25,
"output": 1.25,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072
},
"deepseek-ai/DeepSeek-V3-1": {
"id": "deepseek-ai/DeepSeek-V3-1",
"name": "DeepSeek V3.1",
"api": "openai-completions",
"provider": "together",
"baseUrl": "https://api.together.xyz/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 1.7,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek-ai/DeepSeek-V3.1": {
"id": "deepseek-ai/DeepSeek-V3.1",
"name": "DeepSeek V3.1",
"api": "openai-completions",
"provider": "together",
"baseUrl": "https://api.together.xyz/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 1.25,
"cacheRead": 0.6,
"cacheWrite": 0.6
},
"contextWindow": 131072,
"maxTokens": 8192
},
"deepseek-ai/DeepSeek-V4-Pro": {
"id": "deepseek-ai/DeepSeek-V4-Pro",
"name": "DeepSeek V4 Pro",
"api": "openai-completions",
"provider": "together",
"baseUrl": "https://api.together.xyz/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.74,
"output": 3.48,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 512000,
"maxTokens": 384000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"essentialai/Rnj-1-Instruct": {
"id": "essentialai/Rnj-1-Instruct",
"name": "Rnj-1 Instruct",
"api": "openai-completions",
"provider": "together",
"baseUrl": "https://api.together.xyz/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32768,
"maxTokens": 32768
},
"google/gemma-4-31B-it": {
"id": "google/gemma-4-31B-it",
"name": "Gemma 4 31B Instruct",
"api": "openai-completions",
"provider": "together",
"baseUrl": "https://api.together.xyz/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.39,
"output": 0.97,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"meta-llama/Llama-3.3-70B-Instruct-Turbo": {
"id": "meta-llama/Llama-3.3-70B-Instruct-Turbo",
"name": "Llama 3.3 70B",
"api": "openai-completions",
"provider": "together",
"baseUrl": "https://api.together.xyz/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.88,
"output": 0.88,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072
},
"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": {
"id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
"name": "Llama 4 Maverick 17B 128E Instruct FP8",
"api": "openai-completions",
"provider": "together",
"baseUrl": "https://api.together.xyz/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.27,
"output": 0.85,
"cacheRead": 0.27,
"cacheWrite": 0.27
},
"contextWindow": 20000000,
"maxTokens": 32768
},
"meta-llama/Llama-4-Scout-17B-16E-Instruct": {
"id": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"name": "Llama 4 Scout 17B 16E Instruct",
"api": "openai-completions",
"provider": "together",
"baseUrl": "https://api.together.xyz/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.18,
"output": 0.59,
"cacheRead": 0.18,
"cacheWrite": 0.18
},
"contextWindow": 10000000,
"maxTokens": 32768
},
"MiniMaxAI/MiniMax-M2.5": {
"id": "MiniMaxAI/MiniMax-M2.5",
"name": "MiniMax-M2.5",
"api": "openai-completions",
"provider": "together",
"baseUrl": "https://api.together.xyz/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.06,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"MiniMaxAI/MiniMax-M2.7": {
"id": "MiniMaxAI/MiniMax-M2.7",
"name": "MiniMax-M2.7",
"api": "openai-completions",
"provider": "together",
"baseUrl": "https://api.together.xyz/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.06,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"MiniMaxAI/MiniMax-M3": {
"id": "MiniMaxAI/MiniMax-M3",
"name": "MiniMax-M3",
"api": "openai-completions",
"provider": "together",
"baseUrl": "https://api.together.xyz/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.06,
"cacheWrite": 0
},
"contextWindow": 524288,
"maxTokens": 250000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"moonshotai/Kimi-K2-Instruct-0905": {
"id": "moonshotai/Kimi-K2-Instruct-0905",
"name": "Kimi-K2-Instruct-0905",
"api": "openai-completions",
"provider": "together",
"baseUrl": "https://api.together.xyz/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 3,
"cacheRead": 1,
"cacheWrite": 3
},
"contextWindow": 262144,
"maxTokens": 8192
},
"moonshotai/Kimi-K2.5": {
"id": "moonshotai/Kimi-K2.5",
"name": "Kimi K2.5",
"api": "openai-completions",
"provider": "together",
"baseUrl": "https://api.together.xyz/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.5,
"output": 2.8,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"moonshotai/Kimi-K2.6": {
"id": "moonshotai/Kimi-K2.6",
"name": "Kimi K2.6",
"api": "openai-completions",
"provider": "together",
"baseUrl": "https://api.together.xyz/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.2,
"output": 4.5,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 131000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"moonshotai/Kimi-K2.7-Code": {
"id": "moonshotai/Kimi-K2.7-Code",
"name": "Kimi K2.7 Code",
"api": "openai-completions",
"provider": "together",
"baseUrl": "https://api.together.xyz/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.95,
"output": 4,
"cacheRead": 0.19,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nvidia/nemotron-3-ultra-550b-a55b": {
"id": "nvidia/nemotron-3-ultra-550b-a55b",
"name": "Nemotron 3 Ultra 550B A55B",
"api": "openai-completions",
"provider": "together",
"baseUrl": "https://api.together.xyz/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 3.6,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 512300,
"maxTokens": 512300,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-oss-120b": {
"id": "openai/gpt-oss-120b",
"name": "GPT OSS 120B",
"api": "openai-completions",
"provider": "together",
"baseUrl": "https://api.together.xyz/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
]
}
},
"openai/gpt-oss-20b": {
"id": "openai/gpt-oss-20b",
"name": "GPT OSS 20B",
"api": "openai-completions",
"provider": "together",
"baseUrl": "https://api.together.xyz/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.05,
"output": 0.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
]
}
},
"Qwen/Qwen2.5-7B-Instruct-Turbo": {
"id": "Qwen/Qwen2.5-7B-Instruct-Turbo",
"name": "Qwen 2.5 7B Instruct Turbo",
"api": "openai-completions",
"provider": "together",
"baseUrl": "https://api.together.xyz/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 0.3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32768,
"maxTokens": 32768
},
"Qwen/Qwen3-235B-A22B-Instruct-2507-tput": {
"id": "Qwen/Qwen3-235B-A22B-Instruct-2507-tput",
"name": "Qwen3 235B A22B Instruct 2507 FP8",
"api": "openai-completions",
"provider": "together",
"baseUrl": "https://api.together.xyz/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.2,
"output": 0.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": {
"id": "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8",
"name": "Qwen3 Coder 480B A35B Instruct",
"api": "openai-completions",
"provider": "together",
"baseUrl": "https://api.together.xyz/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 2,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"Qwen/Qwen3-Coder-Next-FP8": {
"id": "Qwen/Qwen3-Coder-Next-FP8",
"name": "Qwen3 Coder Next FP8",
"api": "openai-completions",
"provider": "together",
"baseUrl": "https://api.together.xyz/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.5,
"output": 1.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144
},
"Qwen/Qwen3.5-397B-A17B": {
"id": "Qwen/Qwen3.5-397B-A17B",
"name": "Qwen3.5 397B A17B",
"api": "openai-completions",
"provider": "together",
"baseUrl": "https://api.together.xyz/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.6,
"output": 3.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 130000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"Qwen/Qwen3.5-9B": {
"id": "Qwen/Qwen3.5-9B",
"name": "Qwen3.5 9B",
"api": "openai-completions",
"provider": "together",
"baseUrl": "https://api.together.xyz/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.17,
"output": 0.25,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"Qwen/Qwen3.6-Plus": {
"id": "Qwen/Qwen3.6-Plus",
"name": "Qwen3.6 Plus",
"api": "openai-completions",
"provider": "together",
"baseUrl": "https://api.together.xyz/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.5,
"output": 3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 500000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"Qwen/Qwen3.7-Max": {
"id": "Qwen/Qwen3.7-Max",
"name": "Qwen3.7 Max",
"api": "openai-completions",
"provider": "together",
"baseUrl": "https://api.together.xyz/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 1.25,
"output": 3.75,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 500000
},
"zai-org/GLM-4.7": {
"id": "zai-org/GLM-4.7",
"name": "GLM-4.7",
"api": "openai-completions",
"provider": "together",
"baseUrl": "https://api.together.xyz/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.45,
"output": 2,
"cacheRead": 0.45,
"cacheWrite": 2
},
"contextWindow": 202752,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai-org/GLM-5": {
"id": "zai-org/GLM-5",
"name": "GLM-5",
"api": "openai-completions",
"provider": "together",
"baseUrl": "https://api.together.xyz/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 3.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai-org/GLM-5.1": {
"id": "zai-org/GLM-5.1",
"name": "GLM-5.1",
"api": "openai-completions",
"provider": "together",
"baseUrl": "https://api.together.xyz/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.4,
"output": 4.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
}
},
"umans": {
"umans-coder": {
"id": "umans-coder",
"name": "Umans Coder",
"api": "anthropic-messages",
"provider": "umans",
"baseUrl": "https://api.code.umans.ai",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
},
"compat": {
"escapeBuiltinToolNames": true
}
},
"umans-flash": {
"id": "umans-flash",
"name": "Umans Flash",
"api": "anthropic-messages",
"provider": "umans",
"baseUrl": "https://api.code.umans.ai",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
},
"compat": {
"escapeBuiltinToolNames": true
}
},
"umans-glm-5.1": {
"id": "umans-glm-5.1",
"name": "Umans GLM 5.1",
"api": "anthropic-messages",
"provider": "umans",
"baseUrl": "https://api.code.umans.ai",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 131071,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
},
"compat": {
"escapeBuiltinToolNames": true
}
},
"umans-glm-5.2": {
"id": "umans-glm-5.2",
"name": "Umans GLM 5.2",
"api": "anthropic-messages",
"provider": "umans",
"baseUrl": "https://api.code.umans.ai",
"reasoning": true,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
},
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 405504,
"maxTokens": 131071,
"compat": {
"escapeBuiltinToolNames": true
}
},
"umans-kimi-k2.6": {
"id": "umans-kimi-k2.6",
"name": "Umans Kimi K2.6",
"api": "anthropic-messages",
"provider": "umans",
"baseUrl": "https://api.code.umans.ai",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
},
"compat": {
"escapeBuiltinToolNames": true
}
},
"umans-kimi-k2.7": {
"id": "umans-kimi-k2.7",
"name": "Umans Kimi K2.7 Code",
"api": "anthropic-messages",
"provider": "umans",
"baseUrl": "https://api.code.umans.ai",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
},
"compat": {
"escapeBuiltinToolNames": true
}
},
"umans-qwen3.6-35b-a3b": {
"id": "umans-qwen3.6-35b-a3b",
"name": "Umans Qwen3.6 35B A3B",
"api": "anthropic-messages",
"provider": "umans",
"baseUrl": "https://api.code.umans.ai",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
},
"compat": {
"escapeBuiltinToolNames": true
}
}
},
"venice": {
"aion-labs-aion-2-0": {
"id": "aion-labs-aion-2-0",
"name": "aion-labs-aion-2-0",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": null,
"compat": {
"supportsUsageInStreaming": false
}
},
"aion-labs.aion-2-0": {
"id": "aion-labs.aion-2-0",
"name": "aion-labs.aion-2-0",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null,
"compat": {
"supportsUsageInStreaming": false
}
},
"arcee-trinity-large-thinking": {
"id": "arcee-trinity-large-thinking",
"name": "Trinity Large Thinking",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3125,
"output": 1.125,
"cacheRead": 0.075,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"claude-fable-5": {
"id": "claude-fable-5",
"name": "Claude Fable 5",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 12,
"output": 60,
"cacheRead": 1.2,
"cacheWrite": 15
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-opus-4-5": {
"id": "claude-opus-4-5",
"name": "Claude Opus 4.5",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 6,
"output": 30,
"cacheRead": 0.6,
"cacheWrite": 7.5
},
"contextWindow": 198000,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-opus-4-6": {
"id": "claude-opus-4-6",
"name": "Claude Opus 4.6",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 6,
"output": 30,
"cacheRead": 0.6,
"cacheWrite": 7.5
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-opus-4-6-fast": {
"id": "claude-opus-4-6-fast",
"name": "Claude Opus 4.6 Fast",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 36,
"output": 180,
"cacheRead": 3.6,
"cacheWrite": 45
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-opus-4-7": {
"id": "claude-opus-4-7",
"name": "Claude Opus 4.7",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 6,
"output": 30,
"cacheRead": 0.6,
"cacheWrite": 7.5
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-opus-4-7-fast": {
"id": "claude-opus-4-7-fast",
"name": "Claude Opus 4.7 Fast",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 36,
"output": 180,
"cacheRead": 3.6,
"cacheWrite": 45
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-opus-4-8": {
"id": "claude-opus-4-8",
"name": "Claude Opus 4.8",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 6,
"output": 30,
"cacheRead": 0.6,
"cacheWrite": 7.5
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-opus-4-8-fast": {
"id": "claude-opus-4-8-fast",
"name": "Claude Opus 4.8 Fast",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 12,
"output": 60,
"cacheRead": 1.2,
"cacheWrite": 15
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-opus-45": {
"id": "claude-opus-45",
"name": "Claude Opus 4.5",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 198000,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
},
"compat": {
"supportsUsageInStreaming": false
}
},
"claude-sonnet-4-5": {
"id": "claude-sonnet-4-5",
"name": "Claude Sonnet 4.5",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3.75,
"output": 18.75,
"cacheRead": 0.375,
"cacheWrite": 4.69
},
"contextWindow": 198000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-sonnet-4-6": {
"id": "claude-sonnet-4-6",
"name": "Claude Sonnet 4.6",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3.6,
"output": 18,
"cacheRead": 0.36,
"cacheWrite": 4.5
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"claude-sonnet-45": {
"id": "claude-sonnet-45",
"name": "Claude Sonnet 4.5",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 198000,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
},
"compat": {
"supportsUsageInStreaming": false
}
},
"deepseek-v3.2": {
"id": "deepseek-v3.2",
"name": "DeepSeek V3.2",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.33,
"output": 0.48,
"cacheRead": 0.16,
"cacheWrite": 0
},
"contextWindow": 160000,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek-v4-flash": {
"id": "deepseek-v4-flash",
"name": "DeepSeek V4 Flash",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.17,
"output": 0.35,
"cacheRead": 0.028,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek-v4-pro": {
"id": "deepseek-v4-pro",
"name": "DeepSeek V4 Pro",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.73,
"output": 3.796,
"cacheRead": 0.33,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"e2ee-gemma-3-27b-p": {
"id": "e2ee-gemma-3-27b-p",
"name": "e2ee-gemma-3-27b-p",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 40000,
"maxTokens": null,
"compat": {
"supportsUsageInStreaming": false
}
},
"e2ee-gemma-4-26b-a4b-uncensored-p": {
"id": "e2ee-gemma-4-26b-a4b-uncensored-p",
"name": "e2ee-gemma-4-26b-a4b-uncensored-p",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 64000,
"maxTokens": null,
"compat": {
"supportsUsageInStreaming": false
}
},
"e2ee-gemma-4-31b": {
"id": "e2ee-gemma-4-31b",
"name": "e2ee-gemma-4-31b",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32000,
"maxTokens": 8192,
"compat": {
"supportsUsageInStreaming": false
}
},
"e2ee-glm-4-7-flash-p": {
"id": "e2ee-glm-4-7-flash-p",
"name": "e2ee-glm-4-7-flash-p",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 198000,
"maxTokens": null,
"compat": {
"supportsUsageInStreaming": false
}
},
"e2ee-glm-4-7-p": {
"id": "e2ee-glm-4-7-p",
"name": "e2ee-glm-4-7-p",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": null,
"compat": {
"supportsUsageInStreaming": false
}
},
"e2ee-glm-5": {
"id": "e2ee-glm-5",
"name": "e2ee-glm-5",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 198000,
"maxTokens": 131072,
"compat": {
"supportsUsageInStreaming": false
}
},
"e2ee-glm-5-1": {
"id": "e2ee-glm-5-1",
"name": "e2ee-glm-5-1",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 131072,
"compat": {
"supportsUsageInStreaming": false
}
},
"e2ee-glm-5-2-p": {
"id": "e2ee-glm-5-2-p",
"name": "e2ee-glm-5-2-p",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": null,
"compat": {
"supportsUsageInStreaming": false
}
},
"e2ee-gpt-oss-120b-p": {
"id": "e2ee-gpt-oss-120b-p",
"name": "e2ee-gpt-oss-120b-p",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": null,
"compat": {
"supportsUsageInStreaming": false
}
},
"e2ee-gpt-oss-20b-p": {
"id": "e2ee-gpt-oss-20b-p",
"name": "e2ee-gpt-oss-20b-p",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": null,
"compat": {
"supportsUsageInStreaming": false
}
},
"e2ee-qwen-2-5-7b-p": {
"id": "e2ee-qwen-2-5-7b-p",
"name": "e2ee-qwen-2-5-7b-p",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32000,
"maxTokens": null,
"compat": {
"supportsUsageInStreaming": false
}
},
"e2ee-qwen3-30b-a3b-p": {
"id": "e2ee-qwen3-30b-a3b-p",
"name": "e2ee-qwen3-30b-a3b-p",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": null,
"compat": {
"supportsUsageInStreaming": false
}
},
"e2ee-qwen3-5-122b-a10b": {
"id": "e2ee-qwen3-5-122b-a10b",
"name": "e2ee-qwen3-5-122b-a10b",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": null,
"compat": {
"supportsUsageInStreaming": false
}
},
"e2ee-qwen3-6-35b-a3b": {
"id": "e2ee-qwen3-6-35b-a3b",
"name": "e2ee-qwen3-6-35b-a3b",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32000,
"maxTokens": null,
"compat": {
"supportsUsageInStreaming": false
}
},
"e2ee-qwen3-6-35b-a3b-uncensored-p": {
"id": "e2ee-qwen3-6-35b-a3b-uncensored-p",
"name": "e2ee-qwen3-6-35b-a3b-uncensored-p",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": null,
"compat": {
"supportsUsageInStreaming": false
}
},
"e2ee-qwen3-vl-30b-a3b-p": {
"id": "e2ee-qwen3-vl-30b-a3b-p",
"name": "e2ee-qwen3-vl-30b-a3b-p",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": null,
"compat": {
"supportsUsageInStreaming": false
}
},
"e2ee-venice-uncensored-24b-p": {
"id": "e2ee-venice-uncensored-24b-p",
"name": "e2ee-venice-uncensored-24b-p",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32000,
"maxTokens": null,
"compat": {
"supportsUsageInStreaming": false
}
},
"gemini-3-1-pro-preview": {
"id": "gemini-3-1-pro-preview",
"name": "Gemini 3.1 Pro Preview",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 15,
"cacheRead": 0.5,
"cacheWrite": 0.5
},
"contextWindow": 1000000,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"gemini-3-5-flash": {
"id": "gemini-3-5-flash",
"name": "Gemini 3.5 Flash",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.55,
"output": 9.45,
"cacheRead": 0.155,
"cacheWrite": 0.086
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"gemini-3-flash-preview": {
"id": "gemini-3-flash-preview",
"name": "Gemini 3 Flash Preview",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.7,
"output": 3.75,
"cacheRead": 0.07,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"gemini-3-pro-preview": {
"id": "gemini-3-pro-preview",
"name": "Gemini 3 Pro Preview",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"high"
],
"requiresEffort": true
},
"compat": {
"supportsUsageInStreaming": false
}
},
"gemma-4-uncensored": {
"id": "gemma-4-uncensored",
"name": "Gemma 4 Uncensored",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1625,
"output": 0.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 8192
},
"google-gemma-3-27b-it": {
"id": "google-gemma-3-27b-it",
"name": "Google Gemma 3 27B Instruct",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.12,
"output": 0.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 198000,
"maxTokens": 16384
},
"google-gemma-4-26b-a4b-it": {
"id": "google-gemma-4-26b-a4b-it",
"name": "Google Gemma 4 26B A4B Instruct",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1625,
"output": 0.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"google-gemma-4-31b-it": {
"id": "google-gemma-4-31b-it",
"name": "Google Gemma 4 31B Instruct",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.12,
"output": 0.36,
"cacheRead": 0.09,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"google.gemma-4-26b-a4b-it": {
"id": "google.gemma-4-26b-a4b-it",
"name": "google.gemma-4-26b-a4b-it",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"compat": {
"supportsUsageInStreaming": false
}
},
"google.gemma-4-31b-it": {
"id": "google.gemma-4-31b-it",
"name": "google.gemma-4-31b-it",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768,
"compat": {
"supportsUsageInStreaming": false
}
},
"grok-4-20": {
"id": "grok-4-20",
"name": "Grok 4.20",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.42,
"output": 2.83,
"cacheRead": 0.23,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"grok-4-20-beta": {
"id": "grok-4-20-beta",
"name": "grok-4-20-beta",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null,
"compat": {
"supportsUsageInStreaming": false
}
},
"grok-4-20-multi-agent": {
"id": "grok-4-20-multi-agent",
"name": "grok-4-20-multi-agent",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": null,
"compat": {
"supportsUsageInStreaming": false
}
},
"grok-4-20-multi-agent-beta": {
"id": "grok-4-20-multi-agent-beta",
"name": "grok-4-20-multi-agent-beta",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": null,
"maxTokens": null,
"compat": {
"supportsUsageInStreaming": false
}
},
"grok-4-3": {
"id": "grok-4-3",
"name": "Grok 4.3",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.42,
"output": 2.83,
"cacheRead": 0.23,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"grok-41-fast": {
"id": "grok-41-fast",
"name": "Grok 4.1 Fast",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
},
"compat": {
"supportsUsageInStreaming": false
}
},
"grok-build-0-1": {
"id": "grok-build-0-1",
"name": "Grok Build 0.1",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1,
"output": 2,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"grok-code-fast-1": {
"id": "grok-code-fast-1",
"name": "Grok Code Fast 1",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 10000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
},
"compat": {
"supportsUsageInStreaming": false
}
},
"hermes-3-llama-3.1-405b": {
"id": "hermes-3-llama-3.1-405b",
"name": "Hermes 3 Llama 3.1 405b",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192,
"compat": {
"supportsUsageInStreaming": false
}
},
"kimi-k2-5": {
"id": "kimi-k2-5",
"name": "Kimi K2.5",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.56,
"output": 3.5,
"cacheRead": 0.22,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"kimi-k2-6": {
"id": "kimi-k2-6",
"name": "Kimi K2.6",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.85,
"output": 4.655,
"cacheRead": 0.22,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"kimi-k2-7-code": {
"id": "kimi-k2-7-code",
"name": "Kimi K2.7 Code",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.9,
"output": 4.3,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"kimi-k2-thinking": {
"id": "kimi-k2-thinking",
"name": "Kimi K2 Thinking",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
},
"compat": {
"supportsUsageInStreaming": false
}
},
"llama-3.2-3b": {
"id": "llama-3.2-3b",
"name": "Llama 3.2 3B",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"llama-3.3-70b": {
"id": "llama-3.3-70b",
"name": "Llama 3.3 70B",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.7,
"output": 2.8,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"mercury-2": {
"id": "mercury-2",
"name": "Mercury 2",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3125,
"output": 0.9375,
"cacheRead": 0.03125,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 50000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"minimax-m21": {
"id": "minimax-m21",
"name": "MiniMax M2.1",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 198000,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
},
"compat": {
"supportsUsageInStreaming": false
}
},
"minimax-m25": {
"id": "minimax-m25",
"name": "MiniMax M2.5",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.34,
"output": 1.19,
"cacheRead": 0.04,
"cacheWrite": 0
},
"contextWindow": 198000,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax-m27": {
"id": "minimax-m27",
"name": "MiniMax M2.7",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.375,
"output": 1.5,
"cacheRead": 0.06875,
"cacheWrite": 0
},
"contextWindow": 198000,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax-m3": {
"id": "minimax-m3",
"name": "MiniMax M3",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.06,
"cacheWrite": 0
},
"contextWindow": 500000,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"minimax-m3-preview": {
"id": "minimax-m3-preview",
"name": "MiniMax M3 Preview",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.06,
"cacheWrite": 0
},
"contextWindow": 524288,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"mistral-31-24b": {
"id": "mistral-31-24b",
"name": "Venice Medium",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192,
"compat": {
"supportsUsageInStreaming": false
}
},
"mistral-small-2603": {
"id": "mistral-small-2603",
"name": "Mistral Small 4",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1875,
"output": 0.75,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"mistral-small-3-2-24b-instruct": {
"id": "mistral-small-3-2-24b-instruct",
"name": "Mistral Small 3.2 24B Instruct",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.09375,
"output": 0.25,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 16384
},
"nvidia-nemotron-3-nano-30b-a3b": {
"id": "nvidia-nemotron-3-nano-30b-a3b",
"name": "NVIDIA Nemotron 3 Nano 30B",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.075,
"output": 0.3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"nvidia-nemotron-3-ultra-550b-a55b": {
"id": "nvidia-nemotron-3-ultra-550b-a55b",
"name": "NVIDIA Nemotron 3 Ultra",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.625,
"output": 3.125,
"cacheRead": 0.1875,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nvidia-nemotron-cascade-2-30b-a3b": {
"id": "nvidia-nemotron-cascade-2-30b-a3b",
"name": "Nemotron Cascade 2 30B A3B",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.14,
"output": 0.8,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"olafangensan-glm-4.7-flash-heretic": {
"id": "olafangensan-glm-4.7-flash-heretic",
"name": "GLM 4.7 Flash Heretic",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.14,
"output": 0.8,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 24000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai-gpt-4o-2024-11-20": {
"id": "openai-gpt-4o-2024-11-20",
"name": "GPT-4o",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 3.125,
"output": 12.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai-gpt-4o-mini-2024-07-18": {
"id": "openai-gpt-4o-mini-2024-07-18",
"name": "GPT-4o Mini",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1875,
"output": 0.75,
"cacheRead": 0.09375,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai-gpt-52": {
"id": "openai-gpt-52",
"name": "GPT-5.2",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 2.19,
"output": 17.5,
"cacheRead": 0.219,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai-gpt-52-codex": {
"id": "openai-gpt-52-codex",
"name": "GPT-5.2 Codex",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.19,
"output": 17.5,
"cacheRead": 0.219,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai-gpt-53-codex": {
"id": "openai-gpt-53-codex",
"name": "GPT-5.3 Codex",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.19,
"output": 17.5,
"cacheRead": 0.219,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai-gpt-54": {
"id": "openai-gpt-54",
"name": "GPT-5.4",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3.13,
"output": 18.8,
"cacheRead": 0.313,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai-gpt-54-mini": {
"id": "openai-gpt-54-mini",
"name": "GPT-5.4 Mini",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.9375,
"output": 5.625,
"cacheRead": 0.09375,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai-gpt-54-pro": {
"id": "openai-gpt-54-pro",
"name": "GPT-5.4 Pro",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 37.5,
"output": 225,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai-gpt-55": {
"id": "openai-gpt-55",
"name": "GPT-5.5",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 6.25,
"output": 37.5,
"cacheRead": 0.625,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai-gpt-55-pro": {
"id": "openai-gpt-55-pro",
"name": "GPT-5.5 Pro",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 37.5,
"output": 225,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai-gpt-oss-120b": {
"id": "openai-gpt-oss-120b",
"name": "OpenAI GPT OSS 120B",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.07,
"output": 0.3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"qwen-3-6-plus": {
"id": "qwen-3-6-plus",
"name": "Qwen 3.6 Plus Uncensored",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.625,
"output": 3.75,
"cacheRead": 0.0625,
"cacheWrite": 0.78
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen-3-7-max": {
"id": "qwen-3-7-max",
"name": "Qwen 3.7 Max",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 2.7,
"output": 8.05,
"cacheRead": 0.27,
"cacheWrite": 3.35
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen-3-7-plus": {
"id": "qwen-3-7-plus",
"name": "Qwen 3.7 Plus",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.5,
"output": 2,
"cacheRead": 0.05,
"cacheWrite": 0.625
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen3-235b-a22b-instruct-2507": {
"id": "qwen3-235b-a22b-instruct-2507",
"name": "Qwen 3 235B A22B Instruct 2507",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.75,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"qwen3-235b-a22b-thinking-2507": {
"id": "qwen3-235b-a22b-thinking-2507",
"name": "Qwen 3 235B A22B Thinking 2507",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.45,
"output": 3.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"qwen3-4b": {
"id": "qwen3-4b",
"name": "Venice Small",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32000,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
},
"compat": {
"supportsUsageInStreaming": false
}
},
"qwen3-5-35b-a3b": {
"id": "qwen3-5-35b-a3b",
"name": "Qwen 3.5 35B A3B",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3125,
"output": 1.25,
"cacheRead": 0.15625,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen3-5-397b-a17b": {
"id": "qwen3-5-397b-a17b",
"name": "Qwen 3.5 397B",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.75,
"output": 4.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen3-5-9b": {
"id": "qwen3-5-9b",
"name": "Qwen 3.5 9B",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1,
"output": 0.15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen3-6-27b": {
"id": "qwen3-6-27b",
"name": "Qwen 3.6 27B",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.325,
"output": 3.25,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen3-coder-480b-a35b-instruct": {
"id": "qwen3-coder-480b-a35b-instruct",
"name": "Qwen 3 Coder 480b",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 8192,
"compat": {
"supportsUsageInStreaming": false
}
},
"qwen3-coder-480b-a35b-instruct-turbo": {
"id": "qwen3-coder-480b-a35b-instruct-turbo",
"name": "Qwen 3 Coder 480B Turbo",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.35,
"output": 1.5,
"cacheRead": 0.04,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 65536
},
"qwen3-next-80b": {
"id": "qwen3-next-80b",
"name": "Qwen 3 Next 80b",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.35,
"output": 1.9,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 16384
},
"qwen3-vl-235b-a22b": {
"id": "qwen3-vl-235b-a22b",
"name": "Qwen3 VL 235B",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 1.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 16384
},
"tencent-hy3-preview": {
"id": "tencent-hy3-preview",
"name": "Hy3 Preview",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.063,
"output": 0.21,
"cacheRead": 0.021,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"venice-uncensored": {
"id": "venice-uncensored",
"name": "Venice Uncensored 1.1",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32000,
"maxTokens": 8192,
"compat": {
"supportsUsageInStreaming": false
}
},
"venice-uncensored-1-2": {
"id": "venice-uncensored-1-2",
"name": "Venice Uncensored 1.2",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.2,
"output": 0.9,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"venice-uncensored-role-play": {
"id": "venice-uncensored-role-play",
"name": "Venice Role Play Uncensored",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.5,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"xiaomi-mimo-v2-5": {
"id": "xiaomi-mimo-v2-5",
"name": "MiMo-V2.5",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.175,
"output": 0.35,
"cacheRead": 0.0625,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"z-ai-glm-5-turbo": {
"id": "z-ai-glm-5-turbo",
"name": "GLM 5 Turbo",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.2,
"output": 4,
"cacheRead": 0.24,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"z-ai-glm-5v-turbo": {
"id": "z-ai-glm-5v-turbo",
"name": "GLM 5V Turbo",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.5,
"output": 5,
"cacheRead": 0.3,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai-org-glm-4.6": {
"id": "zai-org-glm-4.6",
"name": "GLM 4.6",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.85,
"output": 2.75,
"cacheRead": 0.3,
"cacheWrite": 0
},
"contextWindow": 198000,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai-org-glm-4.7": {
"id": "zai-org-glm-4.7",
"name": "GLM 4.7",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.55,
"output": 2.65,
"cacheRead": 0.11,
"cacheWrite": 0
},
"contextWindow": 198000,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai-org-glm-4.7-flash": {
"id": "zai-org-glm-4.7-flash",
"name": "GLM 4.7 Flash",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.125,
"output": 0.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai-org-glm-5": {
"id": "zai-org-glm-5",
"name": "GLM 5",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 3.2,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 198000,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai-org-glm-5-1": {
"id": "zai-org-glm-5-1",
"name": "GLM 5.1",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.75,
"output": 5.5,
"cacheRead": 0.325,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 24000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai-org-glm-5-2": {
"id": "zai-org-glm-5-2",
"name": "GLM 5.2",
"api": "openai-completions",
"provider": "venice",
"baseUrl": "https://api.venice.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.75,
"output": 5.5,
"cacheRead": 0.325,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 24000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
}
},
"vercel-ai-gateway": {
"alibaba/qwen-3-14b": {
"id": "alibaba/qwen-3-14b",
"name": "Qwen3-14B",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.12,
"output": 0.24,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 40960,
"maxTokens": 16384,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"alibaba/qwen-3-235b": {
"id": "alibaba/qwen-3-235b",
"name": "Qwen3 235B A22B",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.22,
"output": 0.88,
"cacheRead": 0.6,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 16384,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"alibaba/qwen-3-30b": {
"id": "alibaba/qwen-3-30b",
"name": "Qwen3-30B-A3B",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.12,
"output": 0.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 40960,
"maxTokens": 16384,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"alibaba/qwen-3-32b": {
"id": "alibaba/qwen-3-32b",
"name": "Qwen 3 32B",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.16,
"output": 0.64,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"alibaba/qwen-3.6-max-preview": {
"id": "alibaba/qwen-3.6-max-preview",
"name": "Qwen 3.6 Max Preview",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.3,
"output": 7.8,
"cacheRead": 0.26,
"cacheWrite": 1.625
},
"contextWindow": 240000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"alibaba/qwen3-235b-a22b-thinking": {
"id": "alibaba/qwen3-235b-a22b-thinking",
"name": "Qwen3 VL 235B A22B Thinking",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.39999999999999997,
"output": 4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"alibaba/qwen3-coder": {
"id": "alibaba/qwen3-coder",
"name": "Qwen3 Coder 480B A35B Instruct",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.5,
"output": 7.5,
"cacheRead": 0.3,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"alibaba/qwen3-coder-30b-a3b": {
"id": "alibaba/qwen3-coder-30b-a3b",
"name": "Qwen 3 Coder 30B A3B Instruct",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 8192,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"alibaba/qwen3-coder-next": {
"id": "alibaba/qwen3-coder-next",
"name": "Qwen3 Coder Next",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.5,
"output": 1.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"alibaba/qwen3-coder-plus": {
"id": "alibaba/qwen3-coder-plus",
"name": "Qwen3 Coder Plus",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 5,
"cacheRead": 0.19999999999999998,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65536
},
"alibaba/qwen3-max": {
"id": "alibaba/qwen3-max",
"name": "Qwen3 Max",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.2,
"output": 6,
"cacheRead": 0.24,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortRouting": {
"off": "alibaba/qwen3-max",
"minimal": "alibaba/qwen3-max-thinking",
"low": "alibaba/qwen3-max-thinking",
"medium": "alibaba/qwen3-max-thinking",
"high": "alibaba/qwen3-max-thinking",
"xhigh": "alibaba/qwen3-max-thinking"
}
},
"compat": {
"officialEndpoint": false,
"disableStrictTools": false,
"disableAdaptiveThinking": false,
"supportsEagerToolInputStreaming": true,
"supportsLongCacheRetention": false,
"supportsMidConversationSystem": false,
"supportsForcedToolChoice": true,
"supportsSamplingParams": true,
"requiresToolResultId": false,
"replayUnsignedThinking": false,
"escapeBuiltinToolNames": false
}
},
"alibaba/qwen3-max-preview": {
"id": "alibaba/qwen3-max-preview",
"name": "Qwen3 Max Preview",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 1.2,
"output": 6,
"cacheRead": 0.24,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768
},
"alibaba/qwen3-next-80b-a3b-instruct": {
"id": "alibaba/qwen3-next-80b-a3b-instruct",
"name": "Qwen3 Next 80B A3B Instruct",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 1.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768
},
"alibaba/qwen3-next-80b-a3b-thinking": {
"id": "alibaba/qwen3-next-80b-a3b-thinking",
"name": "Qwen3 Next 80B A3B Thinking",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 1.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"alibaba/qwen3-vl-thinking": {
"id": "alibaba/qwen3-vl-thinking",
"name": "Qwen3 VL 235B A22B Thinking",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.39999999999999997,
"output": 4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"alibaba/qwen3.5-flash": {
"id": "alibaba/qwen3.5-flash",
"name": "Qwen 3.5 Flash",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.09999999999999999,
"output": 0.39999999999999997,
"cacheRead": 0.001,
"cacheWrite": 0.125
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"alibaba/qwen3.5-plus": {
"id": "alibaba/qwen3.5-plus",
"name": "Qwen 3.5 Plus",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.39999999999999997,
"output": 2.4,
"cacheRead": 0.04,
"cacheWrite": 0.5
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"alibaba/qwen3.6-27b": {
"id": "alibaba/qwen3.6-27b",
"name": "Qwen 3.6 27B",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.6,
"output": 3.5999999999999996,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"alibaba/qwen3.6-plus": {
"id": "alibaba/qwen3.6-plus",
"name": "Qwen 3.6 Plus",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.5,
"output": 3,
"cacheRead": 0.09999999999999999,
"cacheWrite": 0.625
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"alibaba/qwen3.7-max": {
"id": "alibaba/qwen3.7-max",
"name": "Qwen 3.7 Max",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 3.75,
"cacheRead": 0.25,
"cacheWrite": 1.5625
},
"contextWindow": 991000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"alibaba/qwen3.7-plus": {
"id": "alibaba/qwen3.7-plus",
"name": "Qwen 3.7 Plus",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.39999999999999997,
"output": 1.5999999999999999,
"cacheRead": 0.08,
"cacheWrite": 0.5
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-3-haiku": {
"id": "anthropic/claude-3-haiku",
"name": "Claude Haiku 3",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 1.25,
"cacheRead": 0.03,
"cacheWrite": 0.3
},
"contextWindow": 200000,
"maxTokens": 4096
},
"anthropic/claude-3.5-haiku": {
"id": "anthropic/claude-3.5-haiku",
"name": "Claude 3.5 Haiku",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.7999999999999999,
"output": 4,
"cacheRead": 0.08,
"cacheWrite": 1
},
"contextWindow": 200000,
"maxTokens": 8192
},
"anthropic/claude-3.5-sonnet": {
"id": "anthropic/claude-3.5-sonnet",
"name": "Claude Sonnet 3.5 v2",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 8192
},
"anthropic/claude-3.5-sonnet-20240620": {
"id": "anthropic/claude-3.5-sonnet-20240620",
"name": "Claude 3.5 Sonnet (2024-06-20)",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 8192
},
"anthropic/claude-3.7-sonnet": {
"id": "anthropic/claude-3.7-sonnet",
"name": "Claude 3.7 Sonnet",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 8192,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-fable-5": {
"id": "anthropic/claude-fable-5",
"name": "Claude Fable 5",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 10,
"output": 50,
"cacheRead": 1,
"cacheWrite": 12.5
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"low": "medium",
"medium": "high",
"high": "xhigh",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"anthropic/claude-haiku-4.5": {
"id": "anthropic/claude-haiku-4.5",
"name": "Claude Haiku 4.5",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1,
"output": 5,
"cacheRead": 0.09999999999999999,
"cacheWrite": 1.25
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-opus-4": {
"id": "anthropic/claude-opus-4",
"name": "Claude Opus 4",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 75,
"cacheRead": 1.5,
"cacheWrite": 18.75
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-opus-4.1": {
"id": "anthropic/claude-opus-4.1",
"name": "Claude Opus 4.1",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 75,
"cacheRead": 1.5,
"cacheWrite": 18.75
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-opus-4.5": {
"id": "anthropic/claude-opus-4.5",
"name": "Claude Opus 4.5",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "anthropic-budget-effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-opus-4.6": {
"id": "anthropic/claude-opus-4.6",
"name": "Claude Opus 4.6",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"xhigh": "max"
}
}
},
"anthropic/claude-opus-4.7": {
"id": "anthropic/claude-opus-4.7",
"name": "Claude Opus 4.7",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"low": "medium",
"medium": "high",
"high": "xhigh",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"anthropic/claude-opus-4.8": {
"id": "anthropic/claude-opus-4.8",
"name": "Claude Opus 4.8",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"low": "medium",
"medium": "high",
"high": "xhigh",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"anthropic/claude-sonnet-4": {
"id": "anthropic/claude-sonnet-4",
"name": "Claude Sonnet 4",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-sonnet-4.5": {
"id": "anthropic/claude-sonnet-4.5",
"name": "Claude Sonnet 4.5",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "anthropic-budget-effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-sonnet-4.6": {
"id": "anthropic/claude-sonnet-4.6",
"name": "Claude Sonnet 4.6",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortMap": {
"minimal": "low"
}
}
},
"arcee-ai/trinity-large-preview": {
"id": "arcee-ai/trinity-large-preview",
"name": "Trinity Large Preview",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.25,
"output": 1,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131000,
"maxTokens": 131000
},
"arcee-ai/trinity-large-thinking": {
"id": "arcee-ai/trinity-large-thinking",
"name": "Trinity Large Thinking",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.25,
"output": 0.8999999999999999,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262100,
"maxTokens": 80000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"bytedance/seed-1.6": {
"id": "bytedance/seed-1.6",
"name": "Seed 1.6",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.25,
"output": 2,
"cacheRead": 0.049999999999999996,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 32000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"cohere/command-a": {
"id": "cohere/command-a",
"name": "Command A",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 2.5,
"output": 10,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 8000
},
"deepseek/deepseek-r1": {
"id": "deepseek/deepseek-r1",
"name": "R1",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.35,
"output": 5.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"deepseek/deepseek-v3": {
"id": "deepseek/deepseek-v3",
"name": "DeepSeek V3 0324",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.27,
"output": 1.12,
"cacheRead": 0.135,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 163840
},
"deepseek/deepseek-v3.1": {
"id": "deepseek/deepseek-v3.1",
"name": "DeepSeek V3.1",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.56,
"output": 1.68,
"cacheRead": 0.28,
"cacheWrite": 0
},
"contextWindow": 163840,
"maxTokens": 8192,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"deepseek/deepseek-v3.1-terminus": {
"id": "deepseek/deepseek-v3.1-terminus",
"name": "DeepSeek V3.1 Terminus",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.27,
"output": 1,
"cacheRead": 0.135,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"deepseek/deepseek-v3.2": {
"id": "deepseek/deepseek-v3.2",
"name": "DeepSeek V3.2",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.28,
"output": 0.42,
"cacheRead": 0.028,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"deepseek/deepseek-v3.2-thinking": {
"id": "deepseek/deepseek-v3.2-thinking",
"name": "DeepSeek V3.2 Thinking",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.62,
"output": 1.85,
"cacheRead": 0.028,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"deepseek/deepseek-v4-flash": {
"id": "deepseek/deepseek-v4-flash",
"name": "DeepSeek V4 Flash",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.14,
"output": 0.28,
"cacheRead": 0.0028,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 384000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"deepseek/deepseek-v4-pro": {
"id": "deepseek/deepseek-v4-pro",
"name": "DeepSeek V4 Pro",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.435,
"output": 0.87,
"cacheRead": 0.0036,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 384000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"google/gemini-2.0-flash": {
"id": "google/gemini-2.0-flash",
"name": "Gemini 2.0 Flash",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0.024999999999999998,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 8192
},
"google/gemini-2.0-flash-lite": {
"id": "google/gemini-2.0-flash-lite",
"name": "Gemini 2.0 Flash Lite",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.075,
"output": 0.3,
"cacheRead": 0.02,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 8192
},
"google/gemini-2.5-flash": {
"id": "google/gemini-2.5-flash",
"name": "Gemini 2.5 Flash",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 2.5,
"cacheRead": 0.03,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"google/gemini-2.5-flash-lite": {
"id": "google/gemini-2.5-flash-lite",
"name": "Gemini 2.5 Flash Lite",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.09999999999999999,
"output": 0.39999999999999997,
"cacheRead": 0.01,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"google/gemini-2.5-flash-lite-preview-09-2025": {
"id": "google/gemini-2.5-flash-lite-preview-09-2025",
"name": "Gemini 2.5 Flash Lite Preview 09-2025",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.09999999999999999,
"output": 0.39999999999999997,
"cacheRead": 0.01,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"google/gemini-2.5-flash-preview-09-2025": {
"id": "google/gemini-2.5-flash-preview-09-2025",
"name": "Gemini 2.5 Flash Preview 09-2025",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 2.5,
"cacheRead": 0.03,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"google/gemini-2.5-pro": {
"id": "google/gemini-2.5-pro",
"name": "Gemini 2.5 Pro",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3-flash": {
"id": "google/gemini-3-flash",
"name": "Gemini 3 Flash",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.5,
"output": 3,
"cacheRead": 0.049999999999999996,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3-pro-preview": {
"id": "google/gemini-3-pro-preview",
"name": "Gemini 3 Pro Preview",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 12,
"cacheRead": 0.19999999999999998,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"low",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3.1-flash-lite": {
"id": "google/gemini-3.1-flash-lite",
"name": "Gemini 3.1 Flash Lite",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 1.5,
"cacheRead": 0.03,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3.1-flash-lite-preview": {
"id": "google/gemini-3.1-flash-lite-preview",
"name": "Gemini 3.1 Flash Lite Preview",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 1.5,
"cacheRead": 0.03,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65000
},
"google/gemini-3.1-pro-preview": {
"id": "google/gemini-3.1-pro-preview",
"name": "Gemini 3.1 Pro (Preview)",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 12,
"cacheRead": 0.19999999999999998,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"low",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3.5-flash": {
"id": "google/gemini-3.5-flash",
"name": "Gemini 3.5 Flash",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.5,
"output": 9,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"google/gemma-4-26b-a4b-it": {
"id": "google/gemma-4-26b-a4b-it",
"name": "Gemma 4 26B A4B",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0.015,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"google/gemma-4-31b-it": {
"id": "google/gemma-4-31b-it",
"name": "Gemma 4 31B",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.14,
"output": 0.39999999999999997,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"inception/mercury-2": {
"id": "inception/mercury-2",
"name": "Mercury 2",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.25,
"output": 0.75,
"cacheRead": 0.024999999999999998,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"inception/mercury-coder-small": {
"id": "inception/mercury-coder-small",
"name": "Mercury Coder Small Beta",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.25,
"output": 1,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32000,
"maxTokens": 16384
},
"kwaipilot/kat-coder-pro-v2": {
"id": "kwaipilot/kat-coder-pro-v2",
"name": "KAT-Coder-Pro V2",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.06,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000
},
"meituan/longcat-flash-chat": {
"id": "meituan/longcat-flash-chat",
"name": "LongCat Flash Chat",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 100000
},
"meituan/longcat-flash-thinking": {
"id": "meituan/longcat-flash-thinking",
"name": "LongCat Flash Thinking",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 1.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"meta/llama-3.1-70b": {
"id": "meta/llama-3.1-70b",
"name": "Llama 3.1 70B Instruct",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.72,
"output": 0.72,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"meta/llama-3.1-8b": {
"id": "meta/llama-3.1-8b",
"name": "Llama 3.1 8B Instruct",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.22,
"output": 0.22,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"meta/llama-3.2-11b": {
"id": "meta/llama-3.2-11b",
"name": "Llama 3.2 11B Vision Instruct",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.16,
"output": 0.16,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"meta/llama-3.2-90b": {
"id": "meta/llama-3.2-90b",
"name": "Llama 3.2 90B Vision Instruct",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.72,
"output": 0.72,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"meta/llama-3.3-70b": {
"id": "meta/llama-3.3-70b",
"name": "Llama 3.3 70B Instruct",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.72,
"output": 0.72,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"meta/llama-4-maverick": {
"id": "meta/llama-4-maverick",
"name": "Llama 4 Maverick 17B Instruct",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.24,
"output": 0.9700000000000001,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"meta/llama-4-scout": {
"id": "meta/llama-4-scout",
"name": "Llama 4 Scout 17B Instruct",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.16999999999999998,
"output": 0.66,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
},
"minimax/minimax-m2": {
"id": "minimax/minimax-m2",
"name": "MiniMax M2",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.03,
"cacheWrite": 0.375
},
"contextWindow": 205000,
"maxTokens": 205000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"minimax/minimax-m2.1": {
"id": "minimax/minimax-m2.1",
"name": "MiniMax M2.1",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.03,
"cacheWrite": 0.375
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"minimax/minimax-m2.1-lightning": {
"id": "minimax/minimax-m2.1-lightning",
"name": "MiniMax M2.1 Lightning",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 2.4,
"cacheRead": 0.03,
"cacheWrite": 0.375
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"minimax/minimax-m2.5": {
"id": "minimax/minimax-m2.5",
"name": "MiniMax M2.5",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.03,
"cacheWrite": 0.375
},
"contextWindow": 204800,
"maxTokens": 131000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"minimax/minimax-m2.5-highspeed": {
"id": "minimax/minimax-m2.5-highspeed",
"name": "MiniMax M2.5 High Speed",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.6,
"output": 2.4,
"cacheRead": 0.03,
"cacheWrite": 0.375
},
"contextWindow": 204800,
"maxTokens": 131000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"minimax/minimax-m2.7": {
"id": "minimax/minimax-m2.7",
"name": "MiniMax M2.7",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.06,
"cacheWrite": 0.375
},
"contextWindow": 204800,
"maxTokens": 131000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"minimax/minimax-m2.7-highspeed": {
"id": "minimax/minimax-m2.7-highspeed",
"name": "MiniMax M2.7 highspeed",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.4,
"cacheRead": 0.06,
"cacheWrite": 0.375
},
"contextWindow": 204800,
"maxTokens": 131100,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"minimax/minimax-m3": {
"id": "minimax/minimax-m3",
"name": "MiniMax-M3",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.06,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 1000000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"mistral/codestral": {
"id": "mistral/codestral",
"name": "Mistral Codestral",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 0.8999999999999999,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4000
},
"mistral/devstral-2": {
"id": "mistral/devstral-2",
"name": "Devstral 2",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.39999999999999997,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000
},
"mistral/devstral-small": {
"id": "mistral/devstral-small",
"name": "Devstral Small 1.1",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.09999999999999999,
"output": 0.3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 64000
},
"mistral/devstral-small-2": {
"id": "mistral/devstral-small-2",
"name": "Devstral Small 2",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.09999999999999999,
"output": 0.3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000
},
"mistral/ministral-3b": {
"id": "mistral/ministral-3b",
"name": "Ministral 3B",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.09999999999999999,
"output": 0.09999999999999999,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4000
},
"mistral/ministral-8b": {
"id": "mistral/ministral-8b",
"name": "Ministral 8B",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4000
},
"mistral/mistral-medium": {
"id": "mistral/mistral-medium",
"name": "Mistral Medium 3.1",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.39999999999999997,
"output": 2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 64000
},
"mistral/mistral-medium-3.5": {
"id": "mistral/mistral-medium-3.5",
"name": "Mistral Medium 3.5",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.5,
"output": 7.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"mistral/mistral-nemo": {
"id": "mistral/mistral-nemo",
"name": "Mistral Nemo 12B",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.02,
"output": 0.04,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072
},
"mistral/mistral-small": {
"id": "mistral/mistral-small",
"name": "Mistral Small",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.09999999999999999,
"output": 0.3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32000,
"maxTokens": 4000
},
"mistral/pixtral-12b": {
"id": "mistral/pixtral-12b",
"name": "Pixtral 12B 2409",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 0.15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4000
},
"mistral/pixtral-large": {
"id": "mistral/pixtral-large",
"name": "Pixtral Large",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4000
},
"moonshotai/kimi-k2": {
"id": "moonshotai/kimi-k2",
"name": "Kimi K2 0711",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.5700000000000001,
"output": 2.3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072
},
"moonshotai/kimi-k2-0905": {
"id": "moonshotai/kimi-k2-0905",
"name": "Kimi K2 0905",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.5,
"cacheRead": 0.3,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 128000
},
"moonshotai/kimi-k2-thinking": {
"id": "moonshotai/kimi-k2-thinking",
"name": "Kimi K2 Thinking",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.5,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 262114,
"maxTokens": 262114,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"moonshotai/kimi-k2-turbo": {
"id": "moonshotai/kimi-k2-turbo",
"name": "Kimi K2 Turbo",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.15,
"output": 8,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 262114,
"maxTokens": 262114,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortRouting": {
"off": "moonshotai/kimi-k2-turbo",
"minimal": "moonshotai/kimi-k2-thinking-turbo",
"low": "moonshotai/kimi-k2-thinking-turbo",
"medium": "moonshotai/kimi-k2-thinking-turbo",
"high": "moonshotai/kimi-k2-thinking-turbo",
"xhigh": "moonshotai/kimi-k2-thinking-turbo"
}
},
"compat": {
"officialEndpoint": false,
"disableStrictTools": false,
"disableAdaptiveThinking": false,
"supportsEagerToolInputStreaming": true,
"supportsLongCacheRetention": false,
"supportsMidConversationSystem": false,
"supportsForcedToolChoice": true,
"supportsSamplingParams": true,
"requiresToolResultId": false,
"replayUnsignedThinking": false
}
},
"moonshotai/kimi-k2.5": {
"id": "moonshotai/kimi-k2.5",
"name": "Kimi K2.5",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.6,
"output": 3,
"cacheRead": 0.09999999999999999,
"cacheWrite": 0
},
"contextWindow": 262114,
"maxTokens": 262114,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"moonshotai/kimi-k2.6": {
"id": "moonshotai/kimi-k2.6",
"name": "Kimi K2.6",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.95,
"output": 4,
"cacheRead": 0.16,
"cacheWrite": 0
},
"contextWindow": 262000,
"maxTokens": 262000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"moonshotai/kimi-k2.7-code": {
"id": "moonshotai/kimi-k2.7-code",
"name": "Kimi K2.7 Code",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.95,
"output": 4,
"cacheRead": 0.19,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 32768,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"moonshotai/kimi-k2.7-code-highspeed": {
"id": "moonshotai/kimi-k2.7-code-highspeed",
"name": "Kimi K2.7 Code High Speed",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.9,
"output": 8,
"cacheRead": 0.38,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nvidia/nemotron-3-super-120b-a12b": {
"id": "nvidia/nemotron-3-super-120b-a12b",
"name": "Nemotron 3 Super",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.15,
"output": 0.65,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 32000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nvidia/nemotron-3-ultra-550b-a55b": {
"id": "nvidia/nemotron-3-ultra-550b-a55b",
"name": "Nemotron 3 Ultra 550B A55B",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.4,
"cacheRead": 0.12,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nvidia/nemotron-nano-12b-v2-vl": {
"id": "nvidia/nemotron-nano-12b-v2-vl",
"name": "Nvidia Nemotron Nano 12B V2 VL",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.19999999999999998,
"output": 0.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"nvidia/nemotron-nano-9b-v2": {
"id": "nvidia/nemotron-nano-9b-v2",
"name": "Nemotron Nano 9B V2",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.06,
"output": 0.22999999999999998,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/codex-mini": {
"id": "openai/codex-mini",
"name": "Codex Mini",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.5,
"output": 6,
"cacheRead": 0.375,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 100000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-4-turbo": {
"id": "openai/gpt-4-turbo",
"name": "GPT-4 Turbo",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 10,
"output": 30,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"openai/gpt-4.1": {
"id": "openai/gpt-4.1",
"name": "GPT-4.1",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 8,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 1047576,
"maxTokens": 32768
},
"openai/gpt-4.1-mini": {
"id": "openai/gpt-4.1-mini",
"name": "GPT-4.1 Mini",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.39999999999999997,
"output": 1.5999999999999999,
"cacheRead": 0.09999999999999999,
"cacheWrite": 0
},
"contextWindow": 1047576,
"maxTokens": 32768
},
"openai/gpt-4.1-nano": {
"id": "openai/gpt-4.1-nano",
"name": "GPT-4.1 Nano",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.09999999999999999,
"output": 0.39999999999999997,
"cacheRead": 0.024999999999999998,
"cacheWrite": 0
},
"contextWindow": 1047576,
"maxTokens": 32768
},
"openai/gpt-4o": {
"id": "openai/gpt-4o",
"name": "GPT-4o",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 10,
"cacheRead": 1.25,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-4o-mini": {
"id": "openai/gpt-4o-mini",
"name": "GPT-4o mini",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0.075,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-5": {
"id": "openai/gpt-5",
"name": "GPT-5",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5-chat": {
"id": "openai/gpt-5-chat",
"name": "GPT 5 Chat",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5-codex": {
"id": "openai/gpt-5-codex",
"name": "GPT-5 Codex",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5-mini": {
"id": "openai/gpt-5-mini",
"name": "GPT-5 Mini",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 2,
"cacheRead": 0.024999999999999998,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5-nano": {
"id": "openai/gpt-5-nano",
"name": "GPT-5 Nano",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.049999999999999996,
"output": 0.39999999999999997,
"cacheRead": 0.005,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5-pro": {
"id": "openai/gpt-5-pro",
"name": "GPT-5 Pro",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 120,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 272000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5.1-codex": {
"id": "openai/gpt-5.1-codex",
"name": "GPT-5.1 Codex",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5.1-codex-max": {
"id": "openai/gpt-5.1-codex-max",
"name": "GPT-5.1-Codex-Max",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5.1-codex-mini": {
"id": "openai/gpt-5.1-codex-mini",
"name": "GPT-5.1-Codex-Mini",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 2,
"cacheRead": 0.024999999999999998,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"medium",
"high"
]
}
},
"openai/gpt-5.1-instant": {
"id": "openai/gpt-5.1-instant",
"name": "GPT-5.1 Instant",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5.1-thinking": {
"id": "openai/gpt-5.1-thinking",
"name": "GPT 5.1 Thinking",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"openai/gpt-5.2": {
"id": "openai/gpt-5.2",
"name": "GPT-5.2",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.2-chat": {
"id": "openai/gpt-5.2-chat",
"name": "GPT-5.2 Chat",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-5.2-codex": {
"id": "openai/gpt-5.2-codex",
"name": "GPT-5.2 Codex",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.2-pro": {
"id": "openai/gpt-5.2-pro",
"name": "GPT-5.2 Pro",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 21,
"output": 168,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.3-chat": {
"id": "openai/gpt-5.3-chat",
"name": "GPT-5.3 Chat",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-5.3-codex": {
"id": "openai/gpt-5.3-codex",
"name": "GPT-5.3 Codex",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.4": {
"id": "openai/gpt-5.4",
"name": "GPT-5.4",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 15,
"cacheRead": 0.25,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.4-mini": {
"id": "openai/gpt-5.4-mini",
"name": "GPT-5.4 Mini",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.75,
"output": 4.5,
"cacheRead": 0.075,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.4-nano": {
"id": "openai/gpt-5.4-nano",
"name": "GPT-5.4 Nano",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.19999999999999998,
"output": 1.25,
"cacheRead": 0.02,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.4-pro": {
"id": "openai/gpt-5.4-pro",
"name": "GPT-5.4 Pro",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 30,
"output": 180,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.5": {
"id": "openai/gpt-5.5",
"name": "GPT-5.5",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 30,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
},
"contextPromotionTarget": "vercel-ai-gateway/openai/gpt-5.4"
},
"openai/gpt-5.5-pro": {
"id": "openai/gpt-5.5-pro",
"name": "GPT-5.5 Pro",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 30,
"output": 180,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
},
"contextPromotionTarget": "vercel-ai-gateway/openai/gpt-5.4"
},
"openai/gpt-oss-120b": {
"id": "openai/gpt-oss-120b",
"name": "GPT OSS 120B",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.35,
"output": 0.75,
"cacheRead": 0.25,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-oss-20b": {
"id": "openai/gpt-oss-20b",
"name": "GPT OSS 20B",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.049999999999999996,
"output": 0.19999999999999998,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-oss-safeguard-20b": {
"id": "openai/gpt-oss-safeguard-20b",
"name": "Safety GPT OSS 20B",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.075,
"output": 0.3,
"cacheRead": 0.037,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 65536,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/o1": {
"id": "openai/o1",
"name": "o1",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 60,
"cacheRead": 7.5,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"openai/o3": {
"id": "openai/o3",
"name": "o3",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 8,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"openai/o3-deep-research": {
"id": "openai/o3-deep-research",
"name": "o3 Deep Research",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 10,
"output": 40,
"cacheRead": 2.5,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"openai/o3-mini": {
"id": "openai/o3-mini",
"name": "o3-mini",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.1,
"output": 4.4,
"cacheRead": 0.55,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"openai/o3-pro": {
"id": "openai/o3-pro",
"name": "o3-pro",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 20,
"output": 80,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"openai/o4-mini": {
"id": "openai/o4-mini",
"name": "o4-mini",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.1,
"output": 4.4,
"cacheRead": 0.275,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"perplexity/sonar": {
"id": "perplexity/sonar",
"name": "Sonar",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 1,
"output": 1,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 127000,
"maxTokens": 8000
},
"perplexity/sonar-pro": {
"id": "perplexity/sonar-pro",
"name": "Sonar Pro",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 8000
},
"prime-intellect/intellect-3": {
"id": "prime-intellect/intellect-3",
"name": "INTELLECT-3",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.19999999999999998,
"output": 1.1,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"stepfun/step-3.5-flash": {
"id": "stepfun/step-3.5-flash",
"name": "Step 3.5 Flash",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.09,
"output": 0.3,
"cacheRead": 0,
"cacheWrite": 0.02
},
"contextWindow": 262114,
"maxTokens": 262114,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"stepfun/step-3.7-flash": {
"id": "stepfun/step-3.7-flash",
"name": "Step 3.7 Flash",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.19999999999999998,
"output": 1.15,
"cacheRead": 0.04,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"vercel/v0-1.0-md": {
"id": "vercel/v0-1.0-md",
"name": "v0-1.0-md",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 32000
},
"vercel/v0-1.5-md": {
"id": "vercel/v0-1.5-md",
"name": "v0-1.5-md",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 32768
},
"xai/grok-2-vision": {
"id": "xai/grok-2-vision",
"name": "Grok 2 Vision",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 10,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32768,
"maxTokens": 32768
},
"xai/grok-3": {
"id": "xai/grok-3",
"name": "Grok 3 Beta",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.75,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072
},
"xai/grok-3-fast": {
"id": "xai/grok-3-fast",
"name": "Grok 3 Fast Beta",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 1.25,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072
},
"xai/grok-3-mini": {
"id": "xai/grok-3-mini",
"name": "Grok 3 Mini Beta",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 0.5,
"cacheRead": 0.075,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072
},
"xai/grok-3-mini-fast": {
"id": "xai/grok-3-mini-fast",
"name": "Grok 3 Mini Fast Beta",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 131072
},
"xai/grok-4": {
"id": "xai/grok-4",
"name": "Grok 4",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.75,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"xai/grok-4-fast-non-reasoning": {
"id": "xai/grok-4-fast-non-reasoning",
"name": "Grok 4 Fast Non-Reasoning",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.19999999999999998,
"output": 0.5,
"cacheRead": 0.049999999999999996,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 256000
},
"xai/grok-4-fast-reasoning": {
"id": "xai/grok-4-fast-reasoning",
"name": "Grok 4 Fast Reasoning",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.19999999999999998,
"output": 0.5,
"cacheRead": 0.049999999999999996,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 256000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"xai/grok-4.1-fast-non-reasoning": {
"id": "xai/grok-4.1-fast-non-reasoning",
"name": "Grok 4.1 Fast Non-Reasoning",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.19999999999999998,
"output": 0.5,
"cacheRead": 0.049999999999999996,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 1000000
},
"xai/grok-4.1-fast-reasoning": {
"id": "xai/grok-4.1-fast-reasoning",
"name": "Grok 4.1 Fast Reasoning",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.19999999999999998,
"output": 0.5,
"cacheRead": 0.049999999999999996,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 1000000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"xai/grok-4.20-multi-agent": {
"id": "xai/grok-4.20-multi-agent",
"name": "Grok 4.20 Multi-Agent",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 2.5,
"cacheRead": 0.19999999999999998,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 2000000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"xai/grok-4.20-multi-agent-beta": {
"id": "xai/grok-4.20-multi-agent-beta",
"name": "Grok 4.20 Multi Agent Beta",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 2.5,
"cacheRead": 0.19999999999999998,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 2000000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"xai/grok-4.20-non-reasoning": {
"id": "xai/grok-4.20-non-reasoning",
"name": "Grok 4.20 Non-Reasoning",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 2.5,
"cacheRead": 0.19999999999999998,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 2000000
},
"xai/grok-4.20-non-reasoning-beta": {
"id": "xai/grok-4.20-non-reasoning-beta",
"name": "Grok 4.20 Beta Non-Reasoning",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 2.5,
"cacheRead": 0.19999999999999998,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 2000000
},
"xai/grok-4.20-reasoning": {
"id": "xai/grok-4.20-reasoning",
"name": "Grok 4.20 Reasoning",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 2.5,
"cacheRead": 0.19999999999999998,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 2000000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"xai/grok-4.20-reasoning-beta": {
"id": "xai/grok-4.20-reasoning-beta",
"name": "Grok 4.20 Beta Reasoning",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 2.5,
"cacheRead": 0.19999999999999998,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 2000000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"xai/grok-4.3": {
"id": "xai/grok-4.3",
"name": "Grok 4.3",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 2.5,
"cacheRead": 0.19999999999999998,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 1000000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"xai/grok-build-0.1": {
"id": "xai/grok-build-0.1",
"name": "Grok Build 0.1",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1,
"output": 2,
"cacheRead": 0.19999999999999998,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"xai/grok-code-fast-1": {
"id": "xai/grok-code-fast-1",
"name": "Grok Code Fast 1",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.19999999999999998,
"output": 1.5,
"cacheRead": 0.02,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"xiaomi/mimo-v2-flash": {
"id": "xiaomi/mimo-v2-flash",
"name": "MiMo-V2-Flash",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.09999999999999999,
"output": 0.3,
"cacheRead": 0.01,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"xiaomi/mimo-v2-pro": {
"id": "xiaomi/mimo-v2-pro",
"name": "MiMo-V2-Pro",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 3,
"cacheRead": 0.19999999999999998,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"xiaomi/mimo-v2.5": {
"id": "xiaomi/mimo-v2.5",
"name": "MiMo-V2.5",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.14,
"output": 0.28,
"cacheRead": 0.0028,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 131100,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"xiaomi/mimo-v2.5-pro": {
"id": "xiaomi/mimo-v2.5-pro",
"name": "MiMo V2.5 Pro",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.435,
"output": 0.87,
"cacheRead": 0.0036,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 131000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai/glm-4.5": {
"id": "zai/glm-4.5",
"name": "GLM-4.5",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.2,
"cacheRead": 0.11,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 96000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai/glm-4.5-air": {
"id": "zai/glm-4.5-air",
"name": "GLM 4.5 Air",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.19999999999999998,
"output": 1.1,
"cacheRead": 0.03,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 96000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai/glm-4.5v": {
"id": "zai/glm-4.5v",
"name": "GLM 4.5V",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.6,
"output": 1.7999999999999998,
"cacheRead": 0.11,
"cacheWrite": 0
},
"contextWindow": 66000,
"maxTokens": 16000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai/glm-4.6": {
"id": "zai/glm-4.6",
"name": "GLM 4.6",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.2,
"cacheRead": 0.11,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 96000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai/glm-4.6v": {
"id": "zai/glm-4.6v",
"name": "GLM-4.6V",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 0.8999999999999999,
"cacheRead": 0.049999999999999996,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 24000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai/glm-4.6v-flash": {
"id": "zai/glm-4.6v-flash",
"name": "GLM-4.6V-Flash",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 24000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai/glm-4.7": {
"id": "zai/glm-4.7",
"name": "GLM 4.7",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 2.25,
"output": 2.75,
"cacheRead": 2.25,
"cacheWrite": 0
},
"contextWindow": 131000,
"maxTokens": 40000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai/glm-4.7-flash": {
"id": "zai/glm-4.7-flash",
"name": "GLM 4.7 Flash",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.07,
"output": 0.39999999999999997,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 131000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai/glm-4.7-flashx": {
"id": "zai/glm-4.7-flashx",
"name": "GLM 4.7 FlashX",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.06,
"output": 0.39999999999999997,
"cacheRead": 0.01,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai/glm-5": {
"id": "zai/glm-5",
"name": "GLM 5",
"api": "anthropic-messages",
"baseUrl": "https://ai-gateway.vercel.sh",
"provider": "vercel-ai-gateway",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 3.1999999999999997,
"cacheRead": 0.19999999999999998,
"cacheWrite": 0
},
"contextWindow": 202800,
"maxTokens": 131100,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai/glm-5-turbo": {
"id": "zai/glm-5-turbo",
"name": "GLM 5 Turbo",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.2,
"output": 4,
"cacheRead": 0.24,
"cacheWrite": 0
},
"contextWindow": 202800,
"maxTokens": 131100,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai/glm-5.1": {
"id": "zai/glm-5.1",
"name": "GLM 5.1",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.4,
"output": 4.4,
"cacheRead": 0.26,
"cacheWrite": 0
},
"contextWindow": 202800,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai/glm-5.2": {
"id": "zai/glm-5.2",
"name": "GLM 5.2",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.4,
"output": 4.4,
"cacheRead": 0.26,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"zai/glm-5v-turbo": {
"id": "zai/glm-5v-turbo",
"name": "GLM 5V Turbo",
"api": "anthropic-messages",
"provider": "vercel-ai-gateway",
"baseUrl": "https://ai-gateway.vercel.sh",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.2,
"output": 4,
"cacheRead": 0.24,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 128000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
}
},
"wafer-pass": {
"GLM-5.1": {
"id": "GLM-5.1",
"name": "GLM-5.1",
"api": "openai-completions",
"provider": "wafer-pass",
"baseUrl": "https://pass.wafer.ai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 65536,
"compat": {
"supportsDeveloperRole": false,
"thinkingFormat": "zai",
"reasoningContentField": "reasoning_content"
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"Qwen3.5-397B-A17B": {
"id": "Qwen3.5-397B-A17B",
"name": "Qwen3.5-397B-A17B",
"api": "openai-completions",
"provider": "wafer-pass",
"baseUrl": "https://pass.wafer.ai/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"compat": {
"supportsDeveloperRole": false
}
}
},
"wafer-serverless": {
"deepseek-v4-flash": {
"id": "deepseek-v4-flash",
"name": "deepseek-v4-flash",
"api": "openai-completions",
"provider": "wafer-serverless",
"baseUrl": "https://pass.wafer.ai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.175,
"output": 0.35,
"cacheRead": 0.0125,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65536,
"compat": {
"supportsDeveloperRole": false,
"reasoningContentField": "reasoning_content"
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek-v4-pro": {
"id": "deepseek-v4-pro",
"name": "deepseek-v4-pro",
"api": "openai-completions",
"provider": "wafer-serverless",
"baseUrl": "https://pass.wafer.ai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 2.175,
"output": 4.35,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 65536,
"compat": {
"supportsDeveloperRole": false,
"reasoningContentField": "reasoning_content"
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"GLM-5.1": {
"id": "GLM-5.1",
"name": "GLM-5.1",
"api": "openai-completions",
"provider": "wafer-serverless",
"baseUrl": "https://pass.wafer.ai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.5,
"output": 4.5,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 202752,
"maxTokens": 65536,
"compat": {
"supportsDeveloperRole": false,
"thinkingFormat": "zai",
"reasoningContentField": "reasoning_content"
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"Kimi-K2.6": {
"id": "Kimi-K2.6",
"name": "Kimi-K2.6",
"api": "openai-completions",
"provider": "wafer-serverless",
"baseUrl": "https://pass.wafer.ai/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.1,
"output": 4.8,
"cacheRead": 0.1125,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"compat": {
"supportsDeveloperRole": false,
"thinkingFormat": "zai",
"reasoningContentField": "reasoning_content"
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"Qwen3.5-397B-A17B": {
"id": "Qwen3.5-397B-A17B",
"name": "Qwen3.5-397B-A17B",
"api": "openai-completions",
"provider": "wafer-serverless",
"baseUrl": "https://pass.wafer.ai/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.6,
"output": 3.6,
"cacheRead": 0.0625,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"compat": {
"supportsDeveloperRole": false
}
},
"Qwen3.6-35B-A3B": {
"id": "Qwen3.6-35B-A3B",
"name": "Qwen3.6-35B-A3B",
"api": "openai-completions",
"provider": "wafer-serverless",
"baseUrl": "https://pass.wafer.ai/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1875,
"output": 1.25,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 65536,
"compat": {
"supportsDeveloperRole": false
}
},
"qwen3.7-max": {
"id": "qwen3.7-max",
"name": "Qwen3.7 Max",
"api": "openai-completions",
"provider": "wafer-serverless",
"baseUrl": "https://pass.wafer.ai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 6.25,
"output": 18.75,
"cacheRead": 0.625,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 65536,
"compat": {
"supportsDeveloperRole": false,
"reasoningContentField": "reasoning_content"
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
}
},
"xai": {
"grok-2": {
"id": "grok-2",
"name": "Grok 2",
"api": "openai-completions",
"provider": "xai",
"baseUrl": "https://api.x.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 2,
"output": 10,
"cacheRead": 2,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192
},
"grok-2-1212": {
"id": "grok-2-1212",
"name": "Grok 2 (1212)",
"api": "openai-completions",
"provider": "xai",
"baseUrl": "https://api.x.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 2,
"output": 10,
"cacheRead": 2,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192
},
"grok-2-latest": {
"id": "grok-2-latest",
"name": "Grok 2 Latest",
"api": "openai-completions",
"provider": "xai",
"baseUrl": "https://api.x.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 2,
"output": 10,
"cacheRead": 2,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192
},
"grok-2-vision": {
"id": "grok-2-vision",
"name": "Grok 2 Vision",
"api": "openai-completions",
"provider": "xai",
"baseUrl": "https://api.x.ai/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 10,
"cacheRead": 2,
"cacheWrite": 0
},
"contextWindow": 8192,
"maxTokens": 4096
},
"grok-2-vision-1212": {
"id": "grok-2-vision-1212",
"name": "Grok 2 Vision (1212)",
"api": "openai-completions",
"provider": "xai",
"baseUrl": "https://api.x.ai/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 10,
"cacheRead": 2,
"cacheWrite": 0
},
"contextWindow": 8192,
"maxTokens": 4096
},
"grok-2-vision-latest": {
"id": "grok-2-vision-latest",
"name": "Grok 2 Vision Latest",
"api": "openai-completions",
"provider": "xai",
"baseUrl": "https://api.x.ai/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 10,
"cacheRead": 2,
"cacheWrite": 0
},
"contextWindow": 8192,
"maxTokens": 4096
},
"grok-3": {
"id": "grok-3",
"name": "Grok 3",
"api": "openai-completions",
"provider": "xai",
"baseUrl": "https://api.x.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.75,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192
},
"grok-3-fast": {
"id": "grok-3-fast",
"name": "Grok 3 Fast",
"api": "openai-completions",
"provider": "xai",
"baseUrl": "https://api.x.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 1.25,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192
},
"grok-3-fast-latest": {
"id": "grok-3-fast-latest",
"name": "Grok 3 Fast Latest",
"api": "openai-completions",
"provider": "xai",
"baseUrl": "https://api.x.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 1.25,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192
},
"grok-3-latest": {
"id": "grok-3-latest",
"name": "Grok 3 Latest",
"api": "openai-completions",
"provider": "xai",
"baseUrl": "https://api.x.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.75,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192
},
"grok-3-mini": {
"id": "grok-3-mini",
"name": "Grok 3 Mini",
"api": "openai-completions",
"provider": "xai",
"baseUrl": "https://api.x.ai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 0.5,
"cacheRead": 0.075,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"grok-3-mini-fast": {
"id": "grok-3-mini-fast",
"name": "Grok 3 Mini Fast",
"api": "openai-completions",
"provider": "xai",
"baseUrl": "https://api.x.ai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 4,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"grok-3-mini-fast-latest": {
"id": "grok-3-mini-fast-latest",
"name": "Grok 3 Mini Fast Latest",
"api": "openai-completions",
"provider": "xai",
"baseUrl": "https://api.x.ai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 4,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"grok-3-mini-latest": {
"id": "grok-3-mini-latest",
"name": "Grok 3 Mini Latest",
"api": "openai-completions",
"provider": "xai",
"baseUrl": "https://api.x.ai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 0.5,
"cacheRead": 0.075,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"grok-4": {
"id": "grok-4",
"name": "Grok 4",
"api": "openai-completions",
"provider": "xai",
"baseUrl": "https://api.x.ai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.75,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"grok-4-1-fast": {
"id": "grok-4-1-fast",
"name": "Grok 4.1 Fast",
"api": "openai-completions",
"provider": "xai",
"baseUrl": "https://api.x.ai/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.2,
"output": 0.5,
"cacheRead": 0.05,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 30000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"grok-4-1-fast-non-reasoning": {
"id": "grok-4-1-fast-non-reasoning",
"name": "Grok 4.1 Fast (Non-Reasoning)",
"api": "openai-completions",
"provider": "xai",
"baseUrl": "https://api.x.ai/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.2,
"output": 0.5,
"cacheRead": 0.05,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 30000
},
"grok-4-fast": {
"id": "grok-4-fast",
"name": "Grok 4 Fast",
"api": "openai-completions",
"provider": "xai",
"baseUrl": "https://api.x.ai/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.2,
"output": 0.5,
"cacheRead": 0.05,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 30000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"grok-4-fast-non-reasoning": {
"id": "grok-4-fast-non-reasoning",
"name": "Grok 4 Fast (Non-Reasoning)",
"api": "openai-completions",
"provider": "xai",
"baseUrl": "https://api.x.ai/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.2,
"output": 0.5,
"cacheRead": 0.05,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 30000
},
"grok-4.20-0309-non-reasoning": {
"id": "grok-4.20-0309-non-reasoning",
"name": "Grok 4.20 (Non-Reasoning)",
"api": "openai-completions",
"provider": "xai",
"baseUrl": "https://api.x.ai/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 2.5,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 30000
},
"grok-4.20-0309-reasoning": {
"id": "grok-4.20-0309-reasoning",
"name": "Grok 4.20 (Reasoning)",
"api": "openai-completions",
"provider": "xai",
"baseUrl": "https://api.x.ai/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 2.5,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 30000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"grok-4.20-beta-latest-non-reasoning": {
"id": "grok-4.20-beta-latest-non-reasoning",
"name": "Grok 4.20 Beta (Non-Reasoning)",
"api": "openai-completions",
"provider": "xai",
"baseUrl": "https://api.x.ai/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 6,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 30000
},
"grok-4.20-beta-latest-reasoning": {
"id": "grok-4.20-beta-latest-reasoning",
"name": "Grok 4.20 Beta (Reasoning)",
"api": "openai-completions",
"provider": "xai",
"baseUrl": "https://api.x.ai/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 6,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 30000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"grok-4.20-multi-agent-beta-latest": {
"id": "grok-4.20-multi-agent-beta-latest",
"name": "Grok 4.20 Multi-Agent Beta",
"api": "openai-completions",
"provider": "xai",
"baseUrl": "https://api.x.ai/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 6,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 30000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"grok-4.3": {
"id": "grok-4.3",
"name": "Grok 4.3",
"api": "openai-completions",
"provider": "xai",
"baseUrl": "https://api.x.ai/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 2.5,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 30000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"grok-beta": {
"id": "grok-beta",
"name": "Grok Beta",
"api": "openai-completions",
"provider": "xai",
"baseUrl": "https://api.x.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 5,
"output": 15,
"cacheRead": 5,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 4096
},
"grok-build-0.1": {
"id": "grok-build-0.1",
"name": "Grok Build 0.1",
"api": "openai-completions",
"provider": "xai",
"baseUrl": "https://api.x.ai/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1,
"output": 2,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"grok-code-fast-1": {
"id": "grok-code-fast-1",
"name": "Grok Code Fast 1",
"api": "openai-completions",
"provider": "xai",
"baseUrl": "https://api.x.ai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.2,
"output": 1.5,
"cacheRead": 0.02,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 10000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"grok-vision-beta": {
"id": "grok-vision-beta",
"name": "Grok Vision Beta",
"api": "openai-completions",
"provider": "xai",
"baseUrl": "https://api.x.ai/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 15,
"cacheRead": 5,
"cacheWrite": 0
},
"contextWindow": 8192,
"maxTokens": 4096
}
},
"xai-oauth": {
"grok-4.20-0309-non-reasoning": {
"id": "grok-4.20-0309-non-reasoning",
"name": "Grok 4.20 (Non-Reasoning)",
"api": "openai-responses",
"provider": "xai-oauth",
"baseUrl": "https://api.x.ai/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 2000000,
"compat": {
"reasoningEffortMap": {
"minimal": "low"
}
}
},
"grok-4.20-0309-reasoning": {
"id": "grok-4.20-0309-reasoning",
"name": "Grok 4.20 (Reasoning)",
"api": "openai-responses",
"provider": "xai-oauth",
"baseUrl": "https://api.x.ai/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 2000000,
"compat": {
"reasoningEffortMap": {
"minimal": "low"
},
"supportsReasoningEffort": false
}
},
"grok-4.20-multi-agent-0309": {
"id": "grok-4.20-multi-agent-0309",
"name": "Grok 4.20 (Multi-Agent)",
"api": "openai-responses",
"provider": "xai-oauth",
"baseUrl": "https://api.x.ai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 2000000,
"compat": {
"reasoningEffortMap": {
"minimal": "low"
}
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low"
}
}
},
"grok-4.3": {
"id": "grok-4.3",
"name": "Grok 4.3",
"api": "openai-responses",
"provider": "xai-oauth",
"baseUrl": "https://api.x.ai/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 1000000,
"compat": {
"reasoningEffortMap": {
"minimal": "low"
}
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low"
}
}
},
"grok-build": {
"id": "grok-build",
"name": "Grok Build",
"api": "openai-responses",
"provider": "xai-oauth",
"baseUrl": "https://api.x.ai/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 512000,
"maxTokens": 512000,
"compat": {
"reasoningEffortMap": {
"minimal": "low"
},
"supportsReasoningEffort": false
}
},
"grok-composer-2.5-fast": {
"id": "grok-composer-2.5-fast",
"name": "Grok Composer 2.5 Fast",
"api": "openai-responses",
"provider": "xai-oauth",
"baseUrl": "https://api.x.ai/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 200000,
"compat": {
"reasoningEffortMap": {
"minimal": "low"
}
}
}
},
"xiaomi": {
"mimo-v2-flash": {
"id": "mimo-v2-flash",
"name": "MiMo-V2-Flash",
"api": "openai-completions",
"provider": "xiaomi",
"baseUrl": "https://api.xiaomimimo.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.1,
"output": 0.3,
"cacheRead": 0.01,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"compat": {
"supportsStore": false,
"thinkingFormat": "zai",
"reasoningContentField": "reasoning_content",
"requiresReasoningContentForToolCalls": true,
"allowsSyntheticReasoningContentForToolCalls": false
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"mimo-v2-omni": {
"id": "mimo-v2-omni",
"name": "MiMo-V2-Omni",
"api": "openai-completions",
"provider": "xiaomi",
"baseUrl": "https://api.xiaomimimo.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.4,
"output": 2,
"cacheRead": 0.08,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 131072,
"compat": {
"supportsStore": false,
"thinkingFormat": "zai",
"reasoningContentField": "reasoning_content",
"requiresReasoningContentForToolCalls": true,
"allowsSyntheticReasoningContentForToolCalls": false
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"mimo-v2-pro": {
"id": "mimo-v2-pro",
"name": "MiMo-V2-Pro",
"api": "openai-completions",
"provider": "xiaomi",
"baseUrl": "https://api.xiaomimimo.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 3,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072,
"compat": {
"supportsStore": false,
"thinkingFormat": "zai",
"reasoningContentField": "reasoning_content",
"requiresReasoningContentForToolCalls": true,
"allowsSyntheticReasoningContentForToolCalls": false
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"mimo-v2.5": {
"id": "mimo-v2.5",
"name": "MiMo-V2.5",
"api": "openai-completions",
"provider": "xiaomi",
"baseUrl": "https://api.xiaomimimo.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.4,
"output": 2,
"cacheRead": 0.08,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072,
"compat": {
"supportsStore": false,
"thinkingFormat": "zai",
"reasoningContentField": "reasoning_content",
"requiresReasoningContentForToolCalls": true,
"allowsSyntheticReasoningContentForToolCalls": false
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"mimo-v2.5-pro": {
"id": "mimo-v2.5-pro",
"name": "MiMo-V2.5-Pro",
"api": "openai-completions",
"provider": "xiaomi",
"baseUrl": "https://api.xiaomimimo.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 3,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072,
"compat": {
"supportsStore": false,
"thinkingFormat": "zai",
"reasoningContentField": "reasoning_content",
"requiresReasoningContentForToolCalls": true,
"allowsSyntheticReasoningContentForToolCalls": false
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"mimo-v2.5-pro-ultraspeed": {
"id": "mimo-v2.5-pro-ultraspeed",
"name": "MiMo-V2.5-Pro-UltraSpeed",
"api": "openai-completions",
"provider": "xiaomi",
"baseUrl": "https://api.xiaomimimo.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.305,
"output": 2.61,
"cacheRead": 0.0108,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072,
"compat": {
"supportsStore": false,
"thinkingFormat": "zai",
"reasoningContentField": "reasoning_content",
"requiresReasoningContentForToolCalls": true,
"allowsSyntheticReasoningContentForToolCalls": false
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
}
},
"xiaomi-token-plan-ams": {
"mimo-v2-omni": {
"id": "mimo-v2-omni",
"name": "MiMo-V2-Omni",
"api": "openai-completions",
"provider": "xiaomi-token-plan-ams",
"baseUrl": "https://token-plan-ams.xiaomimimo.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"mimo-v2-pro": {
"id": "mimo-v2-pro",
"name": "MiMo-V2-Pro",
"api": "openai-completions",
"provider": "xiaomi-token-plan-ams",
"baseUrl": "https://token-plan-ams.xiaomimimo.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"mimo-v2.5": {
"id": "mimo-v2.5",
"name": "MiMo-V2.5",
"api": "openai-completions",
"provider": "xiaomi-token-plan-ams",
"baseUrl": "https://token-plan-ams.xiaomimimo.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"mimo-v2.5-pro": {
"id": "mimo-v2.5-pro",
"name": "MiMo-V2.5-Pro",
"api": "openai-completions",
"provider": "xiaomi-token-plan-ams",
"baseUrl": "https://token-plan-ams.xiaomimimo.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
}
},
"xiaomi-token-plan-cn": {
"mimo-v2-omni": {
"id": "mimo-v2-omni",
"name": "MiMo-V2-Omni",
"api": "openai-completions",
"provider": "xiaomi-token-plan-cn",
"baseUrl": "https://token-plan-cn.xiaomimimo.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"mimo-v2-pro": {
"id": "mimo-v2-pro",
"name": "MiMo-V2-Pro",
"api": "openai-completions",
"provider": "xiaomi-token-plan-cn",
"baseUrl": "https://token-plan-cn.xiaomimimo.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"mimo-v2.5": {
"id": "mimo-v2.5",
"name": "MiMo-V2.5",
"api": "openai-completions",
"provider": "xiaomi-token-plan-cn",
"baseUrl": "https://token-plan-cn.xiaomimimo.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"mimo-v2.5-pro": {
"id": "mimo-v2.5-pro",
"name": "MiMo-V2.5-Pro",
"api": "openai-completions",
"provider": "xiaomi-token-plan-cn",
"baseUrl": "https://token-plan-cn.xiaomimimo.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
}
},
"xiaomi-token-plan-sgp": {
"mimo-v2-omni": {
"id": "mimo-v2-omni",
"name": "MiMo-V2-Omni",
"api": "openai-completions",
"provider": "xiaomi-token-plan-sgp",
"baseUrl": "https://token-plan-sgp.xiaomimimo.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"mimo-v2-pro": {
"id": "mimo-v2-pro",
"name": "MiMo-V2-Pro",
"api": "openai-completions",
"provider": "xiaomi-token-plan-sgp",
"baseUrl": "https://token-plan-sgp.xiaomimimo.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"mimo-v2.5": {
"id": "mimo-v2.5",
"name": "MiMo-V2.5",
"api": "openai-completions",
"provider": "xiaomi-token-plan-sgp",
"baseUrl": "https://token-plan-sgp.xiaomimimo.com/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"mimo-v2.5-pro": {
"id": "mimo-v2.5-pro",
"name": "MiMo-V2.5-Pro",
"api": "openai-completions",
"provider": "xiaomi-token-plan-sgp",
"baseUrl": "https://token-plan-sgp.xiaomimimo.com/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
}
},
"zai": {
"glm-4.5": {
"id": "glm-4.5",
"name": "GLM-4.5",
"api": "anthropic-messages",
"provider": "zai",
"baseUrl": "https://api.z.ai/api/anthropic",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 98304,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"glm-4.5-air": {
"id": "glm-4.5-air",
"name": "GLM-4.5-Air",
"api": "anthropic-messages",
"provider": "zai",
"baseUrl": "https://api.z.ai/api/anthropic",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 98304,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"glm-4.5-flash": {
"id": "glm-4.5-flash",
"name": "GLM-4.5-Flash",
"api": "anthropic-messages",
"provider": "zai",
"baseUrl": "https://api.z.ai/api/anthropic",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 98304,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"glm-4.5v": {
"id": "glm-4.5v",
"name": "GLM-4.5V",
"api": "anthropic-messages",
"provider": "zai",
"baseUrl": "https://api.z.ai/api/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 64000,
"maxTokens": 16384,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"glm-4.6": {
"id": "glm-4.6",
"name": "glm-4.6",
"api": "anthropic-messages",
"provider": "zai",
"baseUrl": "https://api.z.ai/api/anthropic",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"glm-4.6v": {
"id": "glm-4.6v",
"name": "GLM-4.6V",
"api": "anthropic-messages",
"provider": "zai",
"baseUrl": "https://api.z.ai/api/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 32768,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"glm-4.7": {
"id": "glm-4.7",
"name": "GLM-4.7",
"api": "anthropic-messages",
"provider": "zai",
"baseUrl": "https://api.z.ai/api/anthropic",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"glm-4.7-flash": {
"id": "glm-4.7-flash",
"name": "GLM-4.7-Flash",
"api": "anthropic-messages",
"provider": "zai",
"baseUrl": "https://api.z.ai/api/anthropic",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"glm-4.7-flashx": {
"id": "glm-4.7-flashx",
"name": "GLM-4.7-FlashX",
"api": "anthropic-messages",
"provider": "zai",
"baseUrl": "https://api.z.ai/api/anthropic",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.07,
"output": 0.4,
"cacheRead": 0.01,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"glm-5": {
"id": "glm-5",
"name": "GLM-5",
"api": "anthropic-messages",
"provider": "zai",
"baseUrl": "https://api.z.ai/api/anthropic",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"glm-5-turbo": {
"id": "glm-5-turbo",
"name": "GLM-5-Turbo",
"api": "anthropic-messages",
"provider": "zai",
"baseUrl": "https://api.z.ai/api/anthropic",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"glm-5.1": {
"id": "glm-5.1",
"name": "GLM-5.1",
"api": "anthropic-messages",
"provider": "zai",
"baseUrl": "https://api.z.ai/api/anthropic",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"glm-5.2": {
"id": "glm-5.2",
"name": "GLM-5.2",
"api": "anthropic-messages",
"provider": "zai",
"baseUrl": "https://api.z.ai/api/anthropic",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"glm-5v-turbo": {
"id": "glm-5v-turbo",
"name": "GLM-5V-Turbo",
"api": "anthropic-messages",
"provider": "zai",
"baseUrl": "https://api.z.ai/api/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 131072,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
}
},
"zenmux": {
"anthropic/claude-3.5-haiku": {
"id": "anthropic/claude-3.5-haiku",
"name": "Claude 3.5 Haiku",
"api": "anthropic-messages",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/anthropic",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.8,
"output": 4,
"cacheRead": 0.08,
"cacheWrite": 1
},
"contextWindow": 200000,
"maxTokens": 64000
},
"anthropic/claude-3.5-sonnet": {
"id": "anthropic/claude-3.5-sonnet",
"name": "Claude Sonnet 3.5 v2",
"api": "anthropic-messages",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/anthropic",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 8192
},
"anthropic/claude-3.7-sonnet": {
"id": "anthropic/claude-3.7-sonnet",
"name": "Claude 3.7 Sonnet",
"api": "anthropic-messages",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-fable-5": {
"id": "anthropic/claude-fable-5",
"name": "Claude Fable 5",
"api": "anthropic-messages",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 10,
"output": 50,
"cacheRead": 1,
"cacheWrite": 12.5
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"low": "medium",
"medium": "high",
"high": "xhigh",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"anthropic/claude-haiku-4.5": {
"id": "anthropic/claude-haiku-4.5",
"name": "Claude Haiku 4.5",
"api": "anthropic-messages",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/anthropic",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 1,
"output": 5,
"cacheRead": 0.1,
"cacheWrite": 1.25
},
"contextWindow": 200000,
"maxTokens": 64000
},
"anthropic/claude-opus-4": {
"id": "anthropic/claude-opus-4",
"name": "Claude Opus 4",
"api": "anthropic-messages",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 75,
"cacheRead": 1.5,
"cacheWrite": 18.75
},
"contextWindow": 200000,
"maxTokens": 32000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-opus-4.1": {
"id": "anthropic/claude-opus-4.1",
"name": "Claude Opus 4.1",
"api": "anthropic-messages",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 75,
"cacheRead": 1.5,
"cacheWrite": 18.75
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-opus-4.5": {
"id": "anthropic/claude-opus-4.5",
"name": "Claude Opus 4.5",
"api": "anthropic-messages",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "anthropic-budget-effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-opus-4.6": {
"id": "anthropic/claude-opus-4.6",
"name": "Claude Opus 4.6",
"api": "anthropic-messages",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"xhigh": "max"
}
}
},
"anthropic/claude-opus-4.7": {
"id": "anthropic/claude-opus-4.7",
"name": "Claude Opus 4.7",
"api": "anthropic-messages",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"low": "medium",
"medium": "high",
"high": "xhigh",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"anthropic/claude-opus-4.8": {
"id": "anthropic/claude-opus-4.8",
"name": "Claude Opus 4.8",
"api": "anthropic-messages",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 25,
"cacheRead": 0.5,
"cacheWrite": 6.25
},
"contextWindow": 1000000,
"maxTokens": 128000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "low",
"low": "medium",
"medium": "high",
"high": "xhigh",
"xhigh": "max"
},
"supportsDisplay": true
}
},
"anthropic/claude-sonnet-4": {
"id": "anthropic/claude-sonnet-4",
"name": "Claude Sonnet 4",
"api": "anthropic-messages",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "budget",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-sonnet-4.5": {
"id": "anthropic/claude-sonnet-4.5",
"name": "Claude Sonnet 4.5",
"api": "anthropic-messages",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "anthropic-budget-effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"anthropic/claude-sonnet-4.6": {
"id": "anthropic/claude-sonnet-4.6",
"name": "Claude Sonnet 4.6",
"api": "anthropic-messages",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/anthropic",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.3,
"cacheWrite": 3.75
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "anthropic-adaptive",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"effortMap": {
"minimal": "low"
}
}
},
"baidu/ernie-5.0-thinking-preview": {
"id": "baidu/ernie-5.0-thinking-preview",
"name": "ERNIE 5.0",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.84,
"output": 3.37,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"baidu/ernie-5.1": {
"id": "baidu/ernie-5.1",
"name": "ERNIE 5.1",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.588,
"output": 2.646,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": null,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"baidu/ernie-x1.1-preview": {
"id": "baidu/ernie-x1.1-preview",
"name": "ERNIE-X1.1-Preview",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.14,
"output": 0.56,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 65536,
"maxTokens": null,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"bytedance/doubao-seed-1.8": {
"id": "bytedance/doubao-seed-1.8",
"name": "Doubao-Seed-1.8",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.11,
"output": 0.28,
"cacheRead": 0.023,
"cacheWrite": 0.0024
},
"contextWindow": 256000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"bytedance/doubao-seed-2.0-code": {
"id": "bytedance/doubao-seed-2.0-code",
"name": "Doubao-Seed-2.0-Code",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.45,
"output": 2.24,
"cacheRead": 0.09,
"cacheWrite": 0.0024
},
"contextWindow": 256000,
"maxTokens": 32000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"bytedance/doubao-seed-2.0-lite": {
"id": "bytedance/doubao-seed-2.0-lite",
"name": "Doubao-Seed-2.0-lite",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.09,
"output": 0.51,
"cacheRead": 0.02,
"cacheWrite": 0.0024
},
"contextWindow": 256000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"bytedance/doubao-seed-2.0-mini": {
"id": "bytedance/doubao-seed-2.0-mini",
"name": "Doubao-Seed-2.0-mini",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.03,
"output": 0.28,
"cacheRead": 0.01,
"cacheWrite": 0.0024
},
"contextWindow": 256000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"bytedance/doubao-seed-2.0-pro": {
"id": "bytedance/doubao-seed-2.0-pro",
"name": "Doubao-Seed-2.0-pro",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.45,
"output": 2.24,
"cacheRead": 0.09,
"cacheWrite": 0.0024
},
"contextWindow": 256000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"bytedance/doubao-seed-code": {
"id": "bytedance/doubao-seed-code",
"name": "Doubao-Seed-Code",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.17,
"output": 1.12,
"cacheRead": 0.034,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": null,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"deepseek/deepseek-chat": {
"id": "deepseek/deepseek-chat",
"name": "DeepSeek-V3.2 (Non-thinking Mode)",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.28,
"output": 0.42,
"cacheRead": 0.03,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 64000
},
"deepseek/deepseek-chat-v3.1": {
"id": "deepseek/deepseek-chat-v3.1",
"name": "DeepSeek V3.1",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.28,
"output": 1.11,
"cacheRead": 0.056,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek/deepseek-r1-0528": {
"id": "deepseek/deepseek-r1-0528",
"name": "R1 0528",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.56,
"output": 2.23,
"cacheRead": 0.112,
"cacheWrite": 0
},
"contextWindow": 64000,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek/deepseek-reasoner": {
"id": "deepseek/deepseek-reasoner",
"name": "DeepSeek-V3.2 (Thinking Mode)",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.14,
"output": 0.28,
"cacheRead": 0.028,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": null,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
},
"requiresEffort": true
}
},
"deepseek/deepseek-v3.2": {
"id": "deepseek/deepseek-v3.2",
"name": "DeepSeek V3.2",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.28,
"output": 0.43,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek/deepseek-v3.2-exp": {
"id": "deepseek/deepseek-v3.2-exp",
"name": "DeepSeek-V3.2-Exp",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.22,
"output": 0.33,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 163000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek/deepseek-v4-flash": {
"id": "deepseek/deepseek-v4-flash",
"name": "DeepSeek V4 Flash",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.14,
"output": 0.28,
"cacheRead": 0.0028,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 384000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek/deepseek-v4-flash-free": {
"id": "deepseek/deepseek-v4-flash-free",
"name": "DeepSeek V4 Flash (Free)",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 384000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek/deepseek-v4-pro": {
"id": "deepseek/deepseek-v4-pro",
"name": "DeepSeek V4 Pro",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.435,
"output": 0.87,
"cacheRead": 0.003625,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 384000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"deepseek/deepseek-v4-pro-free": {
"id": "deepseek/deepseek-v4-pro-free",
"name": "DeepSeek V4 Pro (Free)",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 384000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "high",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"google/gemini-2.0-flash": {
"id": "google/gemini-2.0-flash",
"name": "Gemini 2.0 Flash",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0.0375,
"cacheWrite": 1
},
"contextWindow": 1048576,
"maxTokens": 8192
},
"google/gemini-2.0-flash-lite-001": {
"id": "google/gemini-2.0-flash-lite-001",
"name": "Gemini 2.0 Flash Lite",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.075,
"output": 0.3,
"cacheRead": 0.01875,
"cacheWrite": 1
},
"contextWindow": 1048576,
"maxTokens": 8192
},
"google/gemini-2.5-flash": {
"id": "google/gemini-2.5-flash",
"name": "Gemini 2.5 Flash",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 2.5,
"cacheRead": 0.07,
"cacheWrite": 1
},
"contextWindow": 1048000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"google/gemini-2.5-flash-lite": {
"id": "google/gemini-2.5-flash-lite",
"name": "Gemini 2.5 Flash Lite",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1,
"output": 0.4,
"cacheRead": 0.03,
"cacheWrite": 1
},
"contextWindow": 1048000,
"maxTokens": 64000
},
"google/gemini-2.5-pro": {
"id": "google/gemini-2.5-pro",
"name": "Gemini 2.5 Pro",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.31,
"cacheWrite": 4.5
},
"contextWindow": 1048000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3-flash-preview": {
"id": "google/gemini-3-flash-preview",
"name": "Gemini 3 Flash Preview",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.5,
"output": 3,
"cacheRead": 0.05,
"cacheWrite": 1
},
"contextWindow": 1048000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3-pro-image-preview": {
"id": "google/gemini-3-pro-image-preview",
"name": "Gemini 3 Pro Image Preview",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 12,
"cacheRead": 0.2,
"cacheWrite": 4.5
},
"contextWindow": 1048000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3-pro-preview": {
"id": "google/gemini-3-pro-preview",
"name": "Gemini 3 Pro Preview",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 12,
"cacheRead": 0.2,
"cacheWrite": 4.5
},
"contextWindow": 1048000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3.1-flash-lite": {
"id": "google/gemini-3.1-flash-lite",
"name": "Gemini 3.1 Flash Lite",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 1.5,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3.1-flash-lite-preview": {
"id": "google/gemini-3.1-flash-lite-preview",
"name": "Gemini 3.1 Flash Lite Preview",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 1.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 65530
},
"google/gemini-3.1-pro-preview": {
"id": "google/gemini-3.1-pro-preview",
"name": "Gemini 3.1 Pro Preview",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 12,
"cacheRead": 0.2,
"cacheWrite": 4.5
},
"contextWindow": 1048000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3.5-flash": {
"id": "google/gemini-3.5-flash",
"name": "Gemini 3.5 Flash",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.5,
"output": 9,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"google/gemini-3.5-flash-free": {
"id": "google/gemini-3.5-flash-free",
"name": "Gemini 3.5 Flash Free",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"google/gemini-embedding-2": {
"id": "google/gemini-embedding-2",
"name": "Gemini Embedding 2",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.2,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 8192,
"maxTokens": null
},
"google/gemma-3-12b-it": {
"id": "google/gemma-3-12b-it",
"name": "Gemma 3 12B",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.024,
"output": 0.096,
"cacheRead": 0.0048,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"inclusionai/ling-1t": {
"id": "inclusionai/ling-1t",
"name": "Ling-1T",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.56,
"output": 2.24,
"cacheRead": 0.11,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 64000
},
"inclusionai/ling-2.6-1t": {
"id": "inclusionai/ling-2.6-1t",
"name": "Ling-2.6-1T",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 2.5,
"cacheRead": 0.06,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768
},
"inclusionai/ling-2.6-flash": {
"id": "inclusionai/ling-2.6-flash",
"name": "Ling-2.6 Flash",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.1,
"output": 0.3,
"cacheRead": 0.02,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768
},
"inclusionai/ling-flash-2.0": {
"id": "inclusionai/ling-flash-2.0",
"name": "Ling-flash-2.0",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.28,
"output": 2.8,
"cacheRead": 0.056,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": null
},
"inclusionai/ling-mini-2.0": {
"id": "inclusionai/ling-mini-2.0",
"name": "Ling-mini-2.0",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.07,
"output": 0.28,
"cacheRead": 0.014,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": null
},
"inclusionai/llada2.0-flash-cap": {
"id": "inclusionai/llada2.0-flash-cap",
"name": "LLaDA2-flash-CAP",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.28,
"output": 2.85,
"cacheRead": 0.057,
"cacheWrite": 0
},
"contextWindow": 32000,
"maxTokens": null
},
"inclusionai/llada2.1-flash": {
"id": "inclusionai/llada2.1-flash",
"name": "LLaDA2.1-flash",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.28,
"output": 2.85,
"cacheRead": 0.057,
"cacheWrite": 0
},
"contextWindow": 32000,
"maxTokens": null
},
"inclusionai/ming-flash-omni-2.0": {
"id": "inclusionai/ming-flash-omni-2.0",
"name": "Ming-flash-omni-2.0",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.8,
"output": 1.8,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 64000,
"maxTokens": null
},
"inclusionai/ring-1t": {
"id": "inclusionai/ring-1t",
"name": "Ring-1T",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.56,
"output": 2.24,
"cacheRead": 0.11,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"inclusionai/ring-2.6-1t": {
"id": "inclusionai/ring-2.6-1t",
"name": "Ring-2.6-1T",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 2.5,
"cacheRead": 0.06,
"cacheWrite": 0
},
"contextWindow": 262000,
"maxTokens": 65000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"inclusionai/ring-flash-2.0": {
"id": "inclusionai/ring-flash-2.0",
"name": "Ring-flash-2.0",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.28,
"output": 2.8,
"cacheRead": 0.056,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": null,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"inclusionai/ring-mini-2.0": {
"id": "inclusionai/ring-mini-2.0",
"name": "Ring-mini-2.0",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.07,
"output": 0.7,
"cacheRead": 0.014,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": null,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"kuaishou/kat-coder-pro-v1": {
"id": "kuaishou/kat-coder-pro-v1",
"name": "KAT-Coder-Pro-V1",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.31,
"output": 1.22,
"cacheRead": 0.061,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": null
},
"kuaishou/kat-coder-pro-v1-free": {
"id": "kuaishou/kat-coder-pro-v1-free",
"name": "KAT-Coder-Pro-V1 Free",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 64000
},
"kuaishou/kat-coder-pro-v2": {
"id": "kuaishou/kat-coder-pro-v2",
"name": "KAT-Coder-Pro-V2",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.06,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 80000
},
"meta/llama-3.3-70b-instruct": {
"id": "meta/llama-3.3-70b-instruct",
"name": "Llama 3.3 70b Instruct",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 1.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 4096
},
"meta/llama-4-scout-17b-16e-instruct": {
"id": "meta/llama-4-scout-17b-16e-instruct",
"name": "Llama 4 Scout Instruct",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.08,
"output": 0.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 32768
},
"minimax/minimax-m2": {
"id": "minimax/minimax-m2",
"name": "MiniMax M2",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.03,
"cacheWrite": 0.38
},
"contextWindow": 204000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax/minimax-m2-her": {
"id": "minimax/minimax-m2-her",
"name": "MiniMax M2-her",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 64000,
"maxTokens": null
},
"minimax/minimax-m2.1": {
"id": "minimax/minimax-m2.1",
"name": "MiniMax M2.1",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.03,
"cacheWrite": 0.38
},
"contextWindow": 204000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax/minimax-m2.5": {
"id": "minimax/minimax-m2.5",
"name": "MiniMax M2.5",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3,
"output": 1.2,
"cacheRead": 0.03,
"cacheWrite": 0.375
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax/minimax-m2.5-lightning": {
"id": "minimax/minimax-m2.5-lightning",
"name": "MiniMax M2.5 highspeed",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 4.8,
"cacheRead": 0.06,
"cacheWrite": 0.75
},
"contextWindow": 204800,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax/minimax-m2.7": {
"id": "minimax/minimax-m2.7",
"name": "MiniMax M2.7",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.3055,
"output": 1.2219,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131070,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax/minimax-m2.7-highspeed": {
"id": "minimax/minimax-m2.7-highspeed",
"name": "MiniMax M2.7 highspeed",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.611,
"output": 2.4439,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131070,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"minimax/minimax-m3": {
"id": "minimax/minimax-m3",
"name": "MiniMax-M3",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.6,
"output": 2.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 512000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"mistralai/mistral-large-2512": {
"id": "mistralai/mistral-large-2512",
"name": "Mistral Large 3 2512",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.5,
"output": 1.5,
"cacheRead": 0.05,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 262144
},
"moonshotai/kimi-k2-0711": {
"id": "moonshotai/kimi-k2-0711",
"name": "Kimi K2 0711",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.56,
"output": 2.23,
"cacheRead": 0.2,
"cacheWrite": 0.003
},
"contextWindow": 32768,
"maxTokens": null
},
"moonshotai/kimi-k2-0905": {
"id": "moonshotai/kimi-k2-0905",
"name": "Kimi K2 0905",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.5,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 262000,
"maxTokens": 64000
},
"moonshotai/kimi-k2-thinking": {
"id": "moonshotai/kimi-k2-thinking",
"name": "Kimi K2 Thinking",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.6,
"output": 2.5,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 262000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"moonshotai/kimi-k2-thinking-turbo": {
"id": "moonshotai/kimi-k2-thinking-turbo",
"name": "Kimi K2 Thinking Turbo",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.15,
"output": 8,
"cacheRead": 0.15,
"cacheWrite": 0
},
"contextWindow": 262000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"moonshotai/kimi-k2.5": {
"id": "moonshotai/kimi-k2.5",
"name": "Kimi K2.5",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.58,
"output": 3.02,
"cacheRead": 0.1,
"cacheWrite": 0
},
"contextWindow": 262000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"moonshotai/kimi-k2.6": {
"id": "moonshotai/kimi-k2.6",
"name": "Kimi K2.6",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.95,
"output": 4,
"cacheRead": 0.16,
"cacheWrite": 0
},
"contextWindow": 262140,
"maxTokens": 262140,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"moonshotai/kimi-k2.7-code": {
"id": "moonshotai/kimi-k2.7-code",
"name": "Kimi K2.7 Code",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.95,
"output": 4,
"cacheRead": 0.16,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"moonshotai/kimi-k2.7-code-free": {
"id": "moonshotai/kimi-k2.7-code-free",
"name": "Kimi K2.7 Code (Free)",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"moonshotai/kimi-k2.7-code-highspeed": {
"id": "moonshotai/kimi-k2.7-code-highspeed",
"name": "Kimi K2.7 Code HighSpeed",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.9,
"output": 8,
"cacheRead": 0.38,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 262144,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/chat-latest": {
"id": "openai/chat-latest",
"name": "Chat Latest (GPT-5.5 Instant)",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 30,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": null
},
"openai/gpt-4.1": {
"id": "openai/gpt-4.1",
"name": "GPT-4.1",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2,
"output": 8,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 1047576,
"maxTokens": 32768
},
"openai/gpt-4.1-mini": {
"id": "openai/gpt-4.1-mini",
"name": "GPT-4.1 Mini",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.4,
"output": 1.6,
"cacheRead": 0.1,
"cacheWrite": 0
},
"contextWindow": 1047576,
"maxTokens": 32768
},
"openai/gpt-4.1-nano": {
"id": "openai/gpt-4.1-nano",
"name": "GPT-4.1 Nano",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1,
"output": 0.4,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 1047576,
"maxTokens": 32768
},
"openai/gpt-4o": {
"id": "openai/gpt-4o",
"name": "GPT-4o",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 2.5,
"output": 10,
"cacheRead": 1.25,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-4o-mini": {
"id": "openai/gpt-4o-mini",
"name": "GPT-4o mini",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.15,
"output": 0.6,
"cacheRead": 0.075,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-5": {
"id": "openai/gpt-5",
"name": "GPT-5",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.12,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5-chat": {
"id": "openai/gpt-5-chat",
"name": "GPT-5 Chat",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.125,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-5-codex": {
"id": "openai/gpt-5-codex",
"name": "GPT-5 Codex",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.12,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5-mini": {
"id": "openai/gpt-5-mini",
"name": "GPT-5 Mini",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 2,
"cacheRead": 0.025,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5-nano": {
"id": "openai/gpt-5-nano",
"name": "GPT-5 Nano",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.05,
"output": 0.4,
"cacheRead": 0.005,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5-pro": {
"id": "openai/gpt-5-pro",
"name": "GPT-5 Pro",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 15,
"output": 120,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 272000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5.1": {
"id": "openai/gpt-5.1",
"name": "GPT-5.1",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.12,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5.1-chat": {
"id": "openai/gpt-5.1-chat",
"name": "GPT-5.1 Chat",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.12,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 64000
},
"openai/gpt-5.1-codex": {
"id": "openai/gpt-5.1-codex",
"name": "GPT-5.1-Codex",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 10,
"cacheRead": 0.12,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"openai/gpt-5.1-codex-mini": {
"id": "openai/gpt-5.1-codex-mini",
"name": "GPT-5.1-Codex-Mini",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 2,
"cacheRead": 0.03,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"medium",
"high"
]
}
},
"openai/gpt-5.2": {
"id": "openai/gpt-5.2",
"name": "GPT-5.2",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.17,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.2-chat": {
"id": "openai/gpt-5.2-chat",
"name": "GPT-5.2 Chat",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.175,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16384
},
"openai/gpt-5.2-codex": {
"id": "openai/gpt-5.2-codex",
"name": "GPT-5.2-Codex",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0.17,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.2-pro": {
"id": "openai/gpt-5.2-pro",
"name": "GPT-5.2-Pro",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 21,
"output": 168,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.3-chat": {
"id": "openai/gpt-5.3-chat",
"name": "GPT-5.3 Chat",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 16380
},
"openai/gpt-5.3-codex": {
"id": "openai/gpt-5.3-codex",
"name": "GPT-5.3 Codex",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.75,
"output": 14,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 272000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.4": {
"id": "openai/gpt-5.4",
"name": "GPT-5.4",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3.75,
"output": 18.75,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.4-mini": {
"id": "openai/gpt-5.4-mini",
"name": "GPT-5.4 Mini",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.75,
"output": 4.5,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000
},
"openai/gpt-5.4-nano": {
"id": "openai/gpt-5.4-nano",
"name": "GPT-5.4 Nano",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.2,
"output": 1.25,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000
},
"openai/gpt-5.4-pro": {
"id": "openai/gpt-5.4-pro",
"name": "GPT-5.4 Pro",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 45,
"output": 225,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
}
},
"openai/gpt-5.5": {
"id": "openai/gpt-5.5",
"name": "GPT-5.5",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 30,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
},
"contextPromotionTarget": "zenmux/openai/gpt-5.4"
},
"openai/gpt-5.5-instant": {
"id": "openai/gpt-5.5-instant",
"name": "GPT-5.5 Instant",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 30,
"cacheRead": 0.5,
"cacheWrite": 0
},
"contextWindow": 400000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
},
"contextPromotionTarget": "zenmux/openai/gpt-5.4"
},
"openai/gpt-5.5-pro": {
"id": "openai/gpt-5.5-pro",
"name": "GPT-5.5 Pro",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 30,
"output": 180,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1050000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"low",
"medium",
"high",
"xhigh"
]
},
"contextPromotionTarget": "zenmux/openai/gpt-5.4"
},
"openai/gpt-image-1.5": {
"id": "openai/gpt-image-1.5",
"name": "GPT-Image-1.5",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 10,
"cacheRead": 1.25,
"cacheWrite": 0
},
"contextWindow": 10000,
"maxTokens": null
},
"openai/gpt-image-2": {
"id": "openai/gpt-image-2",
"name": "GPT-Image-2",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 5,
"output": 0,
"cacheRead": 1.25,
"cacheWrite": 0
},
"contextWindow": 10000,
"maxTokens": null
},
"openai/o4-mini": {
"id": "openai/o4-mini",
"name": "o4-mini",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.1,
"output": 4.4,
"cacheRead": 0.275,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 100000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"openai/text-embedding-3-large": {
"id": "openai/text-embedding-3-large",
"name": "Text Embedding 3 Large",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.13,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 8192,
"maxTokens": null
},
"openai/text-embedding-3-small": {
"id": "openai/text-embedding-3-small",
"name": "Text Embedding 3 Small",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.02,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 8192,
"maxTokens": null
},
"qwen/qwen3-14b": {
"id": "qwen/qwen3-14b",
"name": "Qwen3 14B",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.14,
"output": 1.4,
"cacheRead": 0.028,
"cacheWrite": 0
},
"contextWindow": 32000,
"maxTokens": 40960,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3-235b-a22b-2507": {
"id": "qwen/qwen3-235b-a22b-2507",
"name": "Qwen3 235B A22B Instruct 2507",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.28,
"output": 1.11,
"cacheRead": 0.056,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 16384,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3-235b-a22b-thinking-2507": {
"id": "qwen/qwen3-235b-a22b-thinking-2507",
"name": "Qwen3 235B A22B Thinking 2507",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.28,
"output": 2.78,
"cacheRead": 0.056,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 8192,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
],
"requiresEffort": true
}
},
"qwen/qwen3-asr-flash": {
"id": "qwen/qwen3-asr-flash",
"name": "Qwen3 ASR Flash",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": null,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3-coder": {
"id": "qwen/qwen3-coder",
"name": "Qwen3 Coder 480B A35B",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 1.25,
"output": 5.01,
"cacheRead": 0.25,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 65536
},
"qwen/qwen3-coder-plus": {
"id": "qwen/qwen3-coder-plus",
"name": "Qwen3-Coder-Plus",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 5,
"cacheRead": 0.1,
"cacheWrite": 1.25
},
"contextWindow": 1000000,
"maxTokens": 64000
},
"qwen/qwen3-max": {
"id": "qwen/qwen3-max",
"name": "Qwen3-Max-Thinking",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.2,
"output": 6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3-max-preview": {
"id": "qwen/qwen3-max-preview",
"name": "Qwen3 Max Thinking Preview",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.2,
"output": 6,
"cacheRead": 0.24,
"cacheWrite": 1.5
},
"contextWindow": 262144,
"maxTokens": 32768,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3-vl-embedding": {
"id": "qwen/qwen3-vl-embedding",
"name": "Qwen3 VL Embedding",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.1,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 8192,
"maxTokens": null
},
"qwen/qwen3-vl-plus": {
"id": "qwen/qwen3-vl-plus",
"name": "Qwen3-VL-Plus",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.2,
"output": 1.6,
"cacheRead": 0.02,
"cacheWrite": 0.25
},
"contextWindow": 262144,
"maxTokens": null,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.5-flash": {
"id": "qwen/qwen3.5-flash",
"name": "Qwen3.5 Flash",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1,
"output": 0.4,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1020000,
"maxTokens": 1020000
},
"qwen/qwen3.5-plus": {
"id": "qwen/qwen3.5-plus",
"name": "Qwen3.5 Plus",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.8,
"output": 4.8,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.6-flash": {
"id": "qwen/qwen3.6-flash",
"name": "Qwen3.6 Flash",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.25,
"output": 1.5,
"cacheRead": 0.025,
"cacheWrite": 0.3125
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.6-max-preview": {
"id": "qwen/qwen3.6-max-preview",
"name": "Qwen3.6 Max Preview",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1.3,
"output": 7.8,
"cacheRead": 0.13,
"cacheWrite": 1.625
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.6-plus": {
"id": "qwen/qwen3.6-plus",
"name": "Qwen3.6-Plus",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.5,
"output": 3,
"cacheRead": 0.05,
"cacheWrite": 0.625
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.7-max": {
"id": "qwen/qwen3.7-max",
"name": "Qwen3.7 Max",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 2.5,
"output": 7.5,
"cacheRead": 0.5,
"cacheWrite": 3.125
},
"contextWindow": 1000000,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"qwen/qwen3.7-plus": {
"id": "qwen/qwen3.7-plus",
"name": "Qwen3.7 Plus",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.4,
"output": 1.6,
"cacheRead": 0.08,
"cacheWrite": 0.5
},
"contextWindow": 1000000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"sapiens-ai/agnes-1.5-flash": {
"id": "sapiens-ai/agnes-1.5-flash",
"name": "Agnes-1.5-Flash",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.07,
"output": 0.15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": null,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"sapiens-ai/agnes-1.5-lite": {
"id": "sapiens-ai/agnes-1.5-lite",
"name": "Agnes 1.5 Lite",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.12,
"output": 0.6,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000
},
"sapiens-ai/agnes-1.5-pro": {
"id": "sapiens-ai/agnes-1.5-pro",
"name": "Agnes 1.5 Pro",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.16,
"output": 0.8,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"sapiens-ai/agnes-2.0-flash": {
"id": "sapiens-ai/agnes-2.0-flash",
"name": "Agnes-2.0-Flash",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.1,
"output": 0.2,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": null,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"stepfun/step-3": {
"id": "stepfun/step-3",
"name": "Step-3",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.21,
"output": 0.57,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 65536,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"stepfun/step-3.5-flash": {
"id": "stepfun/step-3.5-flash",
"name": "Step 3.5 Flash",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.1,
"output": 0.3,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 64000
},
"stepfun/step-3.5-flash-free": {
"id": "stepfun/step-3.5-flash-free",
"name": "Step 3.5 Flash (Free)",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"stepfun/step-3.7-flash": {
"id": "stepfun/step-3.7-flash",
"name": "Step 3.7 Flash",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.2,
"output": 1.15,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"stepfun/step-3.7-flash-free": {
"id": "stepfun/step-3.7-flash-free",
"name": "Step 3.7 Flash (Free)",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"tencent/hunyuan-2.0-thinking": {
"id": "tencent/hunyuan-2.0-thinking",
"name": "HY 2.0 Think",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.57,
"output": 2.29,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": null,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"requiresEffort": true
}
},
"tencent/hy3-preview": {
"id": "tencent/hy3-preview",
"name": "Hy3 preview",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.172,
"output": 0.572,
"cacheRead": 0.058,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"volcengine/doubao-seed-1-6-vision": {
"id": "volcengine/doubao-seed-1-6-vision",
"name": "Doubao-Seed-1.6-vision",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.11,
"output": 1.13,
"cacheRead": 0.023,
"cacheWrite": 0.0024
},
"contextWindow": 256000,
"maxTokens": null,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"volcengine/doubao-seed-1.8": {
"id": "volcengine/doubao-seed-1.8",
"name": "Doubao-Seed-1.8",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.11,
"output": 0.28,
"cacheRead": 0.02,
"cacheWrite": 0.0024
},
"contextWindow": 256000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"volcengine/doubao-seed-2.0-code": {
"id": "volcengine/doubao-seed-2.0-code",
"name": "Doubao Seed 2.0 Code",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0.9,
"output": 4.48,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 32000
},
"volcengine/doubao-seed-2.0-lite": {
"id": "volcengine/doubao-seed-2.0-lite",
"name": "Doubao-Seed-2.0-lite",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.09,
"output": 0.51,
"cacheRead": 0.02,
"cacheWrite": 0.0024
},
"contextWindow": 256000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"volcengine/doubao-seed-2.0-mini": {
"id": "volcengine/doubao-seed-2.0-mini",
"name": "Doubao-Seed-2.0-mini",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.03,
"output": 0.28,
"cacheRead": 0.01,
"cacheWrite": 0.0024
},
"contextWindow": 256000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"volcengine/doubao-seed-2.0-pro": {
"id": "volcengine/doubao-seed-2.0-pro",
"name": "Doubao-Seed-2.0-pro",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.45,
"output": 2.24,
"cacheRead": 0.09,
"cacheWrite": 0.0024
},
"contextWindow": 256000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"volcengine/doubao-seed-code": {
"id": "volcengine/doubao-seed-code",
"name": "Doubao-Seed-Code",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.17,
"output": 1.12,
"cacheRead": 0.03,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"x-ai/grok-4": {
"id": "x-ai/grok-4",
"name": "Grok 4",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 15,
"cacheRead": 0.75,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"x-ai/grok-4-fast": {
"id": "x-ai/grok-4-fast",
"name": "Grok 4 Fast",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.2,
"output": 0.5,
"cacheRead": 0.05,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"x-ai/grok-4-fast-non-reasoning": {
"id": "x-ai/grok-4-fast-non-reasoning",
"name": "Grok 4 Fast None Reasoning",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.2,
"output": 0.5,
"cacheRead": 0.05,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 30000
},
"x-ai/grok-4.1-fast": {
"id": "x-ai/grok-4.1-fast",
"name": "Grok 4.1 Fast",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.2,
"output": 0.5,
"cacheRead": 0.05,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"x-ai/grok-4.1-fast-non-reasoning": {
"id": "x-ai/grok-4.1-fast-non-reasoning",
"name": "Grok 4.1 Fast Non Reasoning",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 0.2,
"output": 0.5,
"cacheRead": 0.05,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 64000
},
"x-ai/grok-4.2-fast": {
"id": "x-ai/grok-4.2-fast",
"name": "Grok 4.2 Fast",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 9,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 30000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"x-ai/grok-4.2-fast-non-reasoning": {
"id": "x-ai/grok-4.2-fast-non-reasoning",
"name": "Grok 4.2 Fast Non Reasoning",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text",
"image"
],
"cost": {
"input": 3,
"output": 9,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 2000000,
"maxTokens": 30000
},
"x-ai/grok-4.3": {
"id": "x-ai/grok-4.3",
"name": "Grok 4.3",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1.25,
"output": 2.5,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 1000000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"x-ai/grok-build-0.1": {
"id": "x-ai/grok-build-0.1",
"name": "Grok Build 0.1",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 1,
"output": 2,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 256000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"x-ai/grok-code-fast-1": {
"id": "x-ai/grok-code-fast-1",
"name": "Grok Code Fast 1",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.2,
"output": 1.5,
"cacheRead": 0.02,
"cacheWrite": 0
},
"contextWindow": 256000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"xiaomi/mimo-v2-flash": {
"id": "xiaomi/mimo-v2-flash",
"name": "MiMo-V2-Flash",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.1,
"output": 0.3,
"cacheRead": 0.01,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"xiaomi/mimo-v2-flash-free": {
"id": "xiaomi/mimo-v2-flash-free",
"name": "MiMo-V2-Flash Free",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"xiaomi/mimo-v2-omni": {
"id": "xiaomi/mimo-v2-omni",
"name": "MiMo V2 Omni",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.4,
"output": 2,
"cacheRead": 0.08,
"cacheWrite": 0
},
"contextWindow": 265000,
"maxTokens": 265000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"xiaomi/mimo-v2-pro": {
"id": "xiaomi/mimo-v2-pro",
"name": "MiMo V2 Pro",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 3,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 256000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"xiaomi/mimo-v2.5": {
"id": "xiaomi/mimo-v2.5",
"name": "MiMo-V2.5",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.4,
"output": 2,
"cacheRead": 0.08,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"xiaomi/mimo-v2.5-pro": {
"id": "xiaomi/mimo-v2.5-pro",
"name": "MiMo-V2.5-Pro",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 1,
"output": 3,
"cacheRead": 0.2,
"cacheWrite": 0
},
"contextWindow": 1048576,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"z-ai/glm-4.5": {
"id": "z-ai/glm-4.5",
"name": "GLM 4.5",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.35,
"output": 1.54,
"cacheRead": 0.07,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"z-ai/glm-4.5-air": {
"id": "z-ai/glm-4.5-air",
"name": "GLM 4.5 Air",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.11,
"output": 0.56,
"cacheRead": 0.02,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"z-ai/glm-4.6": {
"id": "z-ai/glm-4.6",
"name": "GLM 4.6",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.35,
"output": 1.54,
"cacheRead": 0.07,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"z-ai/glm-4.6v": {
"id": "z-ai/glm-4.6v",
"name": "GLM 4.6V",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.14,
"output": 0.42,
"cacheRead": 0.03,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"z-ai/glm-4.6v-flash": {
"id": "z-ai/glm-4.6v-flash",
"name": "GLM 4.6V FlashX",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.02,
"output": 0.21,
"cacheRead": 0.0043,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"z-ai/glm-4.6v-flash-free": {
"id": "z-ai/glm-4.6v-flash-free",
"name": "GLM 4.6V Flash (Free)",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"z-ai/glm-4.7": {
"id": "z-ai/glm-4.7",
"name": "GLM 4.7",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.28,
"output": 1.14,
"cacheRead": 0.06,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"z-ai/glm-4.7-flash-free": {
"id": "z-ai/glm-4.7-flash-free",
"name": "GLM 4.7 Flash (Free)",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"z-ai/glm-4.7-flashx": {
"id": "z-ai/glm-4.7-flashx",
"name": "GLM 4.7 FlashX",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.07,
"output": 0.42,
"cacheRead": 0.01,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 64000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"z-ai/glm-5": {
"id": "z-ai/glm-5",
"name": "GLM 5",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.58,
"output": 2.6,
"cacheRead": 0.14,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"z-ai/glm-5-turbo": {
"id": "z-ai/glm-5-turbo",
"name": "GLM 5 Turbo",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.88,
"output": 3.48,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"z-ai/glm-5.1": {
"id": "z-ai/glm-5.1",
"name": "GLM-5.1",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0.8781,
"output": 3.5126,
"cacheRead": 0.1903,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 131072,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
},
"z-ai/glm-5.2": {
"id": "z-ai/glm-5.2",
"name": "GLM 5.2",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 1.4,
"output": 4.4,
"cacheRead": 0.26,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 131072
},
"z-ai/glm-5.2-free": {
"id": "z-ai/glm-5.2-free",
"name": "GLM 5.2 (Free)",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": false,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 131072
},
"z-ai/glm-5v-turbo": {
"id": "z-ai/glm-5v-turbo",
"name": "GLM 5V Turbo",
"api": "openai-completions",
"provider": "zenmux",
"baseUrl": "https://zenmux.ai/api/v1",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.726,
"output": 3.1946,
"cacheRead": 0.1743,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 128000,
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
}
},
"zhipu-coding-plan": {
"glm-4.5-air": {
"id": "glm-4.5-air",
"name": "GLM-4.5-Air",
"api": "openai-completions",
"provider": "zhipu-coding-plan",
"baseUrl": "https://open.bigmodel.cn/api/coding/paas/v4",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 131072,
"maxTokens": 98304,
"compat": {
"thinkingFormat": "zai",
"reasoningContentField": "reasoning_content",
"supportsDeveloperRole": false
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"glm-4.6v": {
"id": "glm-4.6v",
"name": "GLM-4.6V",
"api": "openai-completions",
"provider": "zhipu-coding-plan",
"baseUrl": "https://open.bigmodel.cn/api/coding/paas/v4",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0.3,
"output": 0.9,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 32768,
"compat": {
"thinkingFormat": "zai",
"reasoningContentField": "reasoning_content",
"supportsDeveloperRole": false
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"glm-4.7": {
"id": "glm-4.7",
"name": "GLM-4.7",
"api": "openai-completions",
"provider": "zhipu-coding-plan",
"baseUrl": "https://open.bigmodel.cn/api/coding/paas/v4",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 204800,
"maxTokens": 131072,
"compat": {
"thinkingFormat": "zai",
"reasoningContentField": "reasoning_content",
"supportsDeveloperRole": false
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"glm-5-turbo": {
"id": "glm-5-turbo",
"name": "GLM-5-Turbo",
"api": "openai-completions",
"provider": "zhipu-coding-plan",
"baseUrl": "https://open.bigmodel.cn/api/coding/paas/v4",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 131072,
"compat": {
"thinkingFormat": "zai",
"reasoningContentField": "reasoning_content",
"supportsDeveloperRole": false
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"glm-5.1": {
"id": "glm-5.1",
"name": "GLM-5.1",
"api": "openai-completions",
"provider": "zhipu-coding-plan",
"baseUrl": "https://open.bigmodel.cn/api/coding/paas/v4",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 131072,
"compat": {
"thinkingFormat": "zai",
"reasoningContentField": "reasoning_content",
"supportsDeveloperRole": false
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
},
"glm-5.2": {
"id": "glm-5.2",
"name": "GLM-5.2",
"api": "openai-completions",
"provider": "zhipu-coding-plan",
"baseUrl": "https://open.bigmodel.cn/api/coding/paas/v4",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 1000000,
"maxTokens": 131072,
"compat": {
"thinkingFormat": "zai",
"reasoningContentField": "reasoning_content",
"supportsDeveloperRole": false
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"effortMap": {
"minimal": "none",
"low": "high",
"medium": "high",
"high": "high",
"xhigh": "max"
}
}
},
"glm-5v-turbo": {
"id": "glm-5v-turbo",
"name": "GLM-5V-Turbo",
"api": "openai-completions",
"provider": "zhipu-coding-plan",
"baseUrl": "https://open.bigmodel.cn/api/coding/paas/v4",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 131072,
"compat": {
"thinkingFormat": "zai",
"reasoningContentField": "reasoning_content",
"supportsDeveloperRole": false
},
"thinking": {
"mode": "effort",
"efforts": [
"minimal",
"low",
"medium",
"high"
]
}
}
}
}