# Prime Agent model catalog > Complete provider and model inventory bundled with the audited Prime Agent release. # Prime Agent model catalog This is the complete model catalog bundled with Prime Agent 0.7.0, audited on 2026-08-05. It contains **1,168 models across 32 providers**. A catalog entry means Prime Agent knows how to route that model; it does not mean every model is available to every installation. The usable subset depends on the provider selected through `/login`, its credentials or subscription, account entitlements, region, and current provider availability. Run `prime-agent model list` for the live authenticated subset on a machine. Source: the [official Prime Agent 0.7.0 release artifact](https://pub-728493de92a943e2a9b2d17b4719f318.r2.dev/releases/v0.7.0/prime-agent-ai-0.7.0.tgz), published from [commit `be9e2fa0714e7cd1c6bd9bdb1b554d2cc6550387`](https://github.com/PrimeIntellect-ai/prime-agent/tree/be9e2fa0714e7cd1c6bd9bdb1b554d2cc6550387). The release artifact SHA-256 is `7cdbb3e835f48dd103325f7a351ce540b27af4d161aeb9c7b9bdcc12fe7909af`; the bundled `package/dist/models.generated.js` SHA-256 is `d9d80244b3eee3229554d1643e9c1eeb19fcfb9f79002cf8bb26ec9594075f2b`. ## Provider summary | Provider | Models | | ---------------------- | -----: | | amazon-bedrock | 115 | | anthropic | 15 | | azure-openai-responses | 41 | | cerebras | 3 | | cloudflare-ai-gateway | 43 | | cloudflare-workers-ai | 13 | | deepseek | 2 | | fireworks | 17 | | github-copilot | 29 | | google | 19 | | google-vertex | 13 | | groq | 6 | | huggingface | 55 | | kimi-coding | 4 | | minimax | 2 | | minimax-cn | 2 | | mistral | 31 | | moonshotai | 10 | | moonshotai-cn | 10 | | openai | 41 | | openai-codex | 13 | | opencode | 60 | | opencode-go | 18 | | openrouter | 273 | | prime-inference | 104 | | vercel-ai-gateway | 195 | | xai | 6 | | xiaomi | 6 | | xiaomi-token-plan-ams | 6 | | xiaomi-token-plan-cn | 6 | | xiaomi-token-plan-sgp | 6 | | zai | 4 | ## amazon-bedrock | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | -------------------------------------------------- | ----------------------------------- | ------------------------- | --------: | ---------: | :-------: | ----------- | | `amazon.nova-2-lite-v1:0` | Nova 2 Lite | `bedrock-converse-stream` | 128,000 | 4,096 | yes | text, image | | `amazon.nova-lite-v1:0` | Nova Lite | `bedrock-converse-stream` | 300,000 | 8,192 | no | text, image | | `amazon.nova-micro-v1:0` | Nova Micro | `bedrock-converse-stream` | 128,000 | 8,192 | no | text | | `amazon.nova-pro-v1:0` | Nova Pro | `bedrock-converse-stream` | 300,000 | 8,192 | no | text, image | | `anthropic.claude-fable-5` | Claude Fable 5 | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `anthropic.claude-haiku-4-5-20251001-v1:0` | Claude Haiku 4.5 | `bedrock-converse-stream` | 200,000 | 64,000 | yes | text, image | | `anthropic.claude-opus-4-1-20250805-v1:0` | Claude Opus 4.1 | `bedrock-converse-stream` | 200,000 | 32,000 | yes | text, image | | `anthropic.claude-opus-4-5-20251101-v1:0` | Claude Opus 4.5 | `bedrock-converse-stream` | 200,000 | 64,000 | yes | text, image | | `anthropic.claude-opus-4-6-v1` | Claude Opus 4.6 | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `anthropic.claude-opus-4-7` | Claude Opus 4.7 | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `anthropic.claude-opus-4-8` | Claude Opus 4.8 | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `anthropic.claude-opus-5` | Claude Opus 5 | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `anthropic.claude-sonnet-4-5-20250929-v1:0` | Claude Sonnet 4.5 | `bedrock-converse-stream` | 200,000 | 64,000 | yes | text, image | | `anthropic.claude-sonnet-4-6` | Claude Sonnet 4.6 | `bedrock-converse-stream` | 1,000,000 | 64,000 | yes | text, image | | `anthropic.claude-sonnet-5` | Claude Sonnet 5 | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `au.anthropic.claude-haiku-4-5-20251001-v1:0` | Claude Haiku 4.5 (AU) | `bedrock-converse-stream` | 200,000 | 64,000 | yes | text, image | | `au.anthropic.claude-opus-4-6-v1` | AU Anthropic Claude Opus 4.6 | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `au.anthropic.claude-opus-4-8` | Claude Opus 4.8 (AU) | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `au.anthropic.claude-opus-5` | Claude Opus 5 (AU) | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `au.anthropic.claude-sonnet-4-5-20250929-v1:0` | Claude Sonnet 4.5 (AU) | `bedrock-converse-stream` | 200,000 | 64,000 | yes | text, image | | `au.anthropic.claude-sonnet-4-6` | AU Anthropic Claude Sonnet 4.6 | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `au.anthropic.claude-sonnet-5` | Claude Sonnet 5 (AU) | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `deepseek.r1-v1:0` | DeepSeek-R1 | `bedrock-converse-stream` | 128,000 | 32,768 | yes | text | | `deepseek.v3-v1:0` | DeepSeek-V3.1 | `bedrock-converse-stream` | 163,840 | 81,920 | yes | text | | `deepseek.v3.2` | DeepSeek-V3.2 | `bedrock-converse-stream` | 163,840 | 81,920 | yes | text | | `eu.anthropic.claude-fable-5` | Claude Fable 5 (EU) | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `eu.anthropic.claude-haiku-4-5-20251001-v1:0` | Claude Haiku 4.5 (EU) | `bedrock-converse-stream` | 200,000 | 64,000 | yes | text, image | | `eu.anthropic.claude-opus-4-5-20251101-v1:0` | Claude Opus 4.5 (EU) | `bedrock-converse-stream` | 200,000 | 64,000 | yes | text, image | | `eu.anthropic.claude-opus-4-6-v1` | Claude Opus 4.6 (EU) | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `eu.anthropic.claude-opus-4-7` | Claude Opus 4.7 (EU) | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `eu.anthropic.claude-opus-4-8` | Claude Opus 4.8 (EU) | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `eu.anthropic.claude-opus-5` | Claude Opus 5 (EU) | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `eu.anthropic.claude-sonnet-4-5-20250929-v1:0` | Claude Sonnet 4.5 (EU) | `bedrock-converse-stream` | 200,000 | 64,000 | yes | text, image | | `eu.anthropic.claude-sonnet-4-6` | Claude Sonnet 4.6 (EU) | `bedrock-converse-stream` | 1,000,000 | 64,000 | yes | text, image | | `eu.anthropic.claude-sonnet-5` | Claude Sonnet 5 (EU) | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `global.anthropic.claude-fable-5` | Claude Fable 5 (Global) | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `global.anthropic.claude-haiku-4-5-20251001-v1:0` | Claude Haiku 4.5 (Global) | `bedrock-converse-stream` | 200,000 | 64,000 | yes | text, image | | `global.anthropic.claude-opus-4-5-20251101-v1:0` | Claude Opus 4.5 (Global) | `bedrock-converse-stream` | 200,000 | 64,000 | yes | text, image | | `global.anthropic.claude-opus-4-6-v1` | Claude Opus 4.6 (Global) | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `global.anthropic.claude-opus-4-7` | Claude Opus 4.7 (Global) | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `global.anthropic.claude-opus-4-8` | Claude Opus 4.8 (Global) | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `global.anthropic.claude-opus-5` | Claude Opus 5 (Global) | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `global.anthropic.claude-sonnet-4-5-20250929-v1:0` | Claude Sonnet 4.5 (Global) | `bedrock-converse-stream` | 200,000 | 64,000 | yes | text, image | | `global.anthropic.claude-sonnet-4-6` | Claude Sonnet 4.6 (Global) | `bedrock-converse-stream` | 1,000,000 | 64,000 | yes | text, image | | `global.anthropic.claude-sonnet-5` | Claude Sonnet 5 (Global) | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `google.gemma-3-27b-it` | Google Gemma 3 27B Instruct | `bedrock-converse-stream` | 202,752 | 8,192 | no | text, image | | `google.gemma-3-4b-it` | Gemma 3 4B IT | `bedrock-converse-stream` | 128,000 | 4,096 | no | text, image | | `jp.anthropic.claude-haiku-4-5-20251001-v1:0` | Claude Haiku 4.5 (JP) | `bedrock-converse-stream` | 200,000 | 64,000 | yes | text, image | | `jp.anthropic.claude-opus-4-7` | Claude Opus 4.7 (JP) | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `jp.anthropic.claude-opus-4-8` | Claude Opus 4.8 (JP) | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `jp.anthropic.claude-opus-5` | Claude Opus 5 (JP) | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `jp.anthropic.claude-sonnet-4-5-20250929-v1:0` | Claude Sonnet 4.5 (JP) | `bedrock-converse-stream` | 200,000 | 64,000 | yes | text, image | | `jp.anthropic.claude-sonnet-4-6` | Claude Sonnet 4.6 (JP) | `bedrock-converse-stream` | 1,000,000 | 64,000 | yes | text, image | | `jp.anthropic.claude-sonnet-5` | Claude Sonnet 5 (JP) | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `meta.llama3-1-70b-instruct-v1:0` | Llama 3.1 70B Instruct | `bedrock-converse-stream` | 128,000 | 4,096 | no | text | | `meta.llama3-1-8b-instruct-v1:0` | Llama 3.1 8B Instruct | `bedrock-converse-stream` | 128,000 | 4,096 | no | text | | `meta.llama3-3-70b-instruct-v1:0` | Llama 3.3 70B Instruct | `bedrock-converse-stream` | 128,000 | 4,096 | no | text | | `meta.llama4-maverick-17b-instruct-v1:0` | Llama 4 Maverick 17B Instruct | `bedrock-converse-stream` | 1,000,000 | 16,384 | no | text, image | | `meta.llama4-scout-17b-instruct-v1:0` | Llama 4 Scout 17B Instruct | `bedrock-converse-stream` | 3,500,000 | 16,384 | no | text, image | | `minimax.minimax-m2` | MiniMax M2 | `bedrock-converse-stream` | 204,608 | 128,000 | yes | text | | `minimax.minimax-m2.1` | MiniMax M2.1 | `bedrock-converse-stream` | 204,800 | 131,072 | yes | text | | `minimax.minimax-m2.5` | MiniMax M2.5 | `bedrock-converse-stream` | 196,608 | 98,304 | yes | text | | `mistral.devstral-2-123b` | Devstral 2 123B | `bedrock-converse-stream` | 256,000 | 8,192 | no | text | | `mistral.magistral-small-2509` | Magistral Small 1.2 | `bedrock-converse-stream` | 128,000 | 40,000 | yes | text, image | | `mistral.ministral-3-14b-instruct` | Ministral 14B 3.0 | `bedrock-converse-stream` | 128,000 | 4,096 | no | text | | `mistral.ministral-3-3b-instruct` | Ministral 3 3B | `bedrock-converse-stream` | 256,000 | 8,192 | no | text, image | | `mistral.ministral-3-8b-instruct` | Ministral 3 8B | `bedrock-converse-stream` | 128,000 | 4,096 | no | text | | `mistral.mistral-large-3-675b-instruct` | Mistral Large 3 | `bedrock-converse-stream` | 256,000 | 8,192 | no | text, image | | `mistral.pixtral-large-2502-v1:0` | Pixtral Large (25.02) | `bedrock-converse-stream` | 128,000 | 8,192 | no | text, image | | `mistral.voxtral-mini-3b-2507` | Voxtral Mini 3B 2507 | `bedrock-converse-stream` | 128,000 | 4,096 | no | text | | `mistral.voxtral-small-24b-2507` | Voxtral Small 24B 2507 | `bedrock-converse-stream` | 32,000 | 8,192 | no | text | | `moonshot.kimi-k2-thinking` | Kimi K2 Thinking | `bedrock-converse-stream` | 262,143 | 16,000 | yes | text | | `moonshotai.kimi-k2.5` | Kimi K2.5 | `bedrock-converse-stream` | 262,143 | 16,000 | yes | text, image | | `nvidia.nemotron-nano-12b-v2` | NVIDIA Nemotron Nano 12B v2 VL BF16 | `bedrock-converse-stream` | 128,000 | 4,096 | no | text, image | | `nvidia.nemotron-nano-3-30b` | NVIDIA Nemotron Nano 3 30B | `bedrock-converse-stream` | 128,000 | 4,096 | yes | text | | `nvidia.nemotron-nano-9b-v2` | NVIDIA Nemotron Nano 9B v2 | `bedrock-converse-stream` | 128,000 | 4,096 | no | text | | `nvidia.nemotron-super-3-120b` | NVIDIA Nemotron 3 Super 120B A12B | `bedrock-converse-stream` | 262,144 | 131,072 | yes | text | | `openai.gpt-5.4` | GPT-5.4 | `bedrock-converse-stream` | 272,000 | 128,000 | yes | text, image | | `openai.gpt-5.5` | GPT-5.5 | `bedrock-converse-stream` | 272,000 | 128,000 | yes | text, image | | `openai.gpt-5.6-luna` | GPT-5.6 Luna | `bedrock-converse-stream` | 272,000 | 128,000 | yes | text, image | | `openai.gpt-5.6-sol` | GPT-5.6 Sol | `bedrock-converse-stream` | 272,000 | 128,000 | yes | text, image | | `openai.gpt-5.6-terra` | GPT-5.6 Terra | `bedrock-converse-stream` | 272,000 | 128,000 | yes | text, image | | `openai.gpt-oss-120b` | gpt-oss-120b | `bedrock-converse-stream` | 128,000 | 16,384 | yes | text | | `openai.gpt-oss-120b-1:0` | gpt-oss-120b | `bedrock-converse-stream` | 128,000 | 16,384 | yes | text | | `openai.gpt-oss-20b` | gpt-oss-20b | `bedrock-converse-stream` | 128,000 | 16,384 | yes | text | | `openai.gpt-oss-20b-1:0` | gpt-oss-20b | `bedrock-converse-stream` | 128,000 | 16,384 | yes | text | | `openai.gpt-oss-safeguard-120b` | GPT OSS Safeguard 120B | `bedrock-converse-stream` | 128,000 | 16,384 | no | text | | `openai.gpt-oss-safeguard-20b` | GPT OSS Safeguard 20B | `bedrock-converse-stream` | 128,000 | 16,384 | no | text | | `qwen.qwen3-235b-a22b-2507-v1:0` | Qwen3 235B A22B 2507 | `bedrock-converse-stream` | 262,144 | 131,072 | no | text | | `qwen.qwen3-32b-v1:0` | Qwen3 32B (dense) | `bedrock-converse-stream` | 16,384 | 16,384 | yes | text | | `qwen.qwen3-coder-30b-a3b-v1:0` | Qwen3 Coder 30B A3B Instruct | `bedrock-converse-stream` | 262,144 | 131,072 | no | text | | `qwen.qwen3-coder-480b-a35b-v1:0` | Qwen3 Coder 480B A35B Instruct | `bedrock-converse-stream` | 131,072 | 65,536 | no | text | | `qwen.qwen3-coder-next` | Qwen3 Coder Next | `bedrock-converse-stream` | 131,072 | 65,536 | yes | text | | `qwen.qwen3-next-80b-a3b` | Qwen/Qwen3-Next-80B-A3B-Instruct | `bedrock-converse-stream` | 262,000 | 262,000 | no | text | | `qwen.qwen3-vl-235b-a22b` | Qwen/Qwen3-VL-235B-A22B-Instruct | `bedrock-converse-stream` | 262,000 | 262,000 | no | text, image | | `us.anthropic.claude-fable-5` | Claude Fable 5 (US) | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `us.anthropic.claude-haiku-4-5-20251001-v1:0` | Claude Haiku 4.5 (US) | `bedrock-converse-stream` | 200,000 | 64,000 | yes | text, image | | `us.anthropic.claude-opus-4-1-20250805-v1:0` | Claude Opus 4.1 (US) | `bedrock-converse-stream` | 200,000 | 32,000 | yes | text, image | | `us.anthropic.claude-opus-4-5-20251101-v1:0` | Claude Opus 4.5 (US) | `bedrock-converse-stream` | 200,000 | 64,000 | yes | text, image | | `us.anthropic.claude-opus-4-6-v1` | Claude Opus 4.6 (US) | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `us.anthropic.claude-opus-4-7` | Claude Opus 4.7 (US) | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `us.anthropic.claude-opus-4-8` | Claude Opus 4.8 (US) | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `us.anthropic.claude-opus-5` | Claude Opus 5 (US) | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `us.anthropic.claude-sonnet-4-5-20250929-v1:0` | Claude Sonnet 4.5 (US) | `bedrock-converse-stream` | 200,000 | 64,000 | yes | text, image | | `us.anthropic.claude-sonnet-4-6` | Claude Sonnet 4.6 (US) | `bedrock-converse-stream` | 1,000,000 | 64,000 | yes | text, image | | `us.anthropic.claude-sonnet-5` | Claude Sonnet 5 (US) | `bedrock-converse-stream` | 1,000,000 | 128,000 | yes | text, image | | `us.deepseek.r1-v1:0` | DeepSeek-R1 (US) | `bedrock-converse-stream` | 128,000 | 32,768 | yes | text | | `us.meta.llama4-maverick-17b-instruct-v1:0` | Llama 4 Maverick 17B Instruct (US) | `bedrock-converse-stream` | 1,000,000 | 16,384 | no | text, image | | `us.meta.llama4-scout-17b-instruct-v1:0` | Llama 4 Scout 17B Instruct (US) | `bedrock-converse-stream` | 3,500,000 | 16,384 | no | text, image | | `writer.palmyra-x4-v1:0` | Palmyra X4 | `bedrock-converse-stream` | 122,880 | 8,192 | yes | text | | `writer.palmyra-x5-v1:0` | Palmyra X5 | `bedrock-converse-stream` | 1,040,000 | 8,192 | yes | text | | `xai.grok-4.3` | Grok 4.3 | `bedrock-converse-stream` | 1,000,000 | 131,072 | yes | text, image | | `zai.glm-4.7` | GLM-4.7 | `bedrock-converse-stream` | 204,800 | 131,072 | yes | text | | `zai.glm-4.7-flash` | GLM-4.7-Flash | `bedrock-converse-stream` | 200,000 | 131,072 | yes | text | | `zai.glm-5` | GLM-5 | `bedrock-converse-stream` | 202,752 | 101,376 | yes | text | ## anthropic | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | ---------------------------- | -------------------------- | -------------------- | --------: | ---------: | :-------: | ----------- | | `claude-fable-5` | Claude Fable 5 | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `claude-haiku-4-5` | Claude Haiku 4.5 (latest) | `anthropic-messages` | 200,000 | 64,000 | yes | text, image | | `claude-haiku-4-5-20251001` | Claude Haiku 4.5 | `anthropic-messages` | 200,000 | 64,000 | yes | text, image | | `claude-opus-4-1` | Claude Opus 4.1 (latest) | `anthropic-messages` | 200,000 | 32,000 | yes | text, image | | `claude-opus-4-1-20250805` | Claude Opus 4.1 | `anthropic-messages` | 200,000 | 32,000 | yes | text, image | | `claude-opus-4-5` | Claude Opus 4.5 (latest) | `anthropic-messages` | 200,000 | 64,000 | yes | text, image | | `claude-opus-4-5-20251101` | Claude Opus 4.5 | `anthropic-messages` | 200,000 | 64,000 | yes | text, image | | `claude-opus-4-6` | Claude Opus 4.6 | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `claude-opus-4-7` | Claude Opus 4.7 | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `claude-opus-4-8` | Claude Opus 4.8 | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `claude-opus-5` | Claude Opus 5 | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `claude-sonnet-4-5` | Claude Sonnet 4.5 (latest) | `anthropic-messages` | 1,000,000 | 64,000 | yes | text, image | | `claude-sonnet-4-5-20250929` | Claude Sonnet 4.5 | `anthropic-messages` | 1,000,000 | 64,000 | yes | text, image | | `claude-sonnet-4-6` | Claude Sonnet 4.6 | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `claude-sonnet-5` | Claude Sonnet 5 | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | ## azure-openai-responses | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | --------------------- | --------------------- | ------------------------ | --------: | ---------: | :-------: | ----------- | | `gpt-4` | GPT-4 | `azure-openai-responses` | 8,192 | 8,192 | no | text | | `gpt-4-turbo` | GPT-4 Turbo | `azure-openai-responses` | 128,000 | 4,096 | no | text, image | | `gpt-4.1` | GPT-4.1 | `azure-openai-responses` | 1,047,576 | 32,768 | no | text, image | | `gpt-4.1-mini` | GPT-4.1 mini | `azure-openai-responses` | 1,047,576 | 32,768 | no | text, image | | `gpt-4.1-nano` | GPT-4.1 nano | `azure-openai-responses` | 1,047,576 | 32,768 | no | text, image | | `gpt-4o` | GPT-4o | `azure-openai-responses` | 128,000 | 16,384 | no | text, image | | `gpt-4o-2024-05-13` | GPT-4o (2024-05-13) | `azure-openai-responses` | 128,000 | 4,096 | no | text, image | | `gpt-4o-2024-08-06` | GPT-4o (2024-08-06) | `azure-openai-responses` | 128,000 | 16,384 | no | text, image | | `gpt-4o-2024-11-20` | GPT-4o (2024-11-20) | `azure-openai-responses` | 128,000 | 16,384 | no | text, image | | `gpt-4o-mini` | GPT-4o mini | `azure-openai-responses` | 128,000 | 16,384 | no | text, image | | `gpt-5` | GPT-5 | `azure-openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5-chat-latest` | GPT-5 Chat Latest | `azure-openai-responses` | 128,000 | 16,384 | no | text, image | | `gpt-5-mini` | GPT-5 Mini | `azure-openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5-nano` | GPT-5 Nano | `azure-openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5-pro` | GPT-5 Pro | `azure-openai-responses` | 400,000 | 272,000 | yes | text, image | | `gpt-5.1` | GPT-5.1 | `azure-openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.1-codex` | GPT-5.1 Codex | `azure-openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.1-codex-max` | GPT-5.1 Codex Max | `azure-openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.2` | GPT-5.2 | `azure-openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.2-chat-latest` | GPT-5.2 Chat | `azure-openai-responses` | 128,000 | 16,384 | yes | text, image | | `gpt-5.2-pro` | GPT-5.2 Pro | `azure-openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.3-chat-latest` | GPT-5.3 Chat (latest) | `azure-openai-responses` | 128,000 | 16,384 | no | text, image | | `gpt-5.3-codex` | GPT-5.3 Codex | `azure-openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.3-codex-spark` | GPT-5.3 Codex Spark | `azure-openai-responses` | 128,000 | 32,000 | yes | text, image | | `gpt-5.4` | GPT-5.4 | `azure-openai-responses` | 272,000 | 128,000 | yes | text, image | | `gpt-5.4-mini` | GPT-5.4 mini | `azure-openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.4-nano` | GPT-5.4 nano | `azure-openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.4-pro` | GPT-5.4 Pro | `azure-openai-responses` | 1,050,000 | 128,000 | yes | text, image | | `gpt-5.5` | GPT-5.5 | `azure-openai-responses` | 272,000 | 128,000 | yes | text, image | | `gpt-5.5-pro` | GPT-5.5 Pro | `azure-openai-responses` | 1,050,000 | 128,000 | yes | text, image | | `gpt-5.6` | GPT-5.6 | `azure-openai-responses` | 1,050,000 | 128,000 | yes | text, image | | `gpt-5.6-luna` | GPT-5.6 Luna | `azure-openai-responses` | 1,050,000 | 128,000 | yes | text, image | | `gpt-5.6-sol` | GPT-5.6 Sol | `azure-openai-responses` | 1,050,000 | 128,000 | yes | text, image | | `gpt-5.6-terra` | GPT-5.6 Terra | `azure-openai-responses` | 1,050,000 | 128,000 | yes | text, image | | `gpt-realtime-2.1` | GPT-Realtime-2.1 | `azure-openai-responses` | 128,000 | 32,000 | yes | text, image | | `o1` | o1 | `azure-openai-responses` | 200,000 | 100,000 | yes | text, image | | `o1-pro` | o1-pro | `azure-openai-responses` | 200,000 | 100,000 | yes | text, image | | `o3` | o3 | `azure-openai-responses` | 200,000 | 100,000 | yes | text, image | | `o3-mini` | o3-mini | `azure-openai-responses` | 200,000 | 100,000 | yes | text | | `o3-pro` | o3-pro | `azure-openai-responses` | 200,000 | 100,000 | yes | text, image | | `o4-mini` | o4-mini | `azure-openai-responses` | 200,000 | 100,000 | yes | text, image | ## cerebras | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | -------------- | -------------- | -------------------- | ------: | ---------: | :-------: | ----------- | | `gemma-4-31b` | Gemma 4 31B IT | `openai-completions` | 131,072 | 40,960 | yes | text, image | | `gpt-oss-120b` | GPT OSS 120B | `openai-completions` | 131,072 | 40,960 | yes | text | | `zai-glm-4.7` | Z.AI GLM-4.7 | `openai-completions` | 131,072 | 40,960 | yes | text | ## cloudflare-ai-gateway | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | -------------------------------------------- | -------------------------- | -------------------- | --------: | ---------: | :-------: | ----------- | | `claude-3-5-haiku` | Claude Haiku 3.5 (latest) | `anthropic-messages` | 200,000 | 8,192 | no | text, image | | `claude-3-haiku` | Claude Haiku 3 | `anthropic-messages` | 200,000 | 4,096 | no | text, image | | `claude-3-opus` | Claude Opus 3 | `anthropic-messages` | 200,000 | 4,096 | no | text, image | | `claude-3-sonnet` | Claude Sonnet 3 | `anthropic-messages` | 200,000 | 4,096 | no | text, image | | `claude-3.5-haiku` | Claude Haiku 3.5 (latest) | `anthropic-messages` | 200,000 | 8,192 | no | text, image | | `claude-3.5-sonnet` | Claude Sonnet 3.5 v2 | `anthropic-messages` | 200,000 | 8,192 | no | text, image | | `claude-fable-5` | Claude Fable 5 | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `claude-haiku-4-5` | Claude Haiku 4.5 (latest) | `anthropic-messages` | 200,000 | 64,000 | yes | text, image | | `claude-opus-4` | Claude Opus 4 (latest) | `anthropic-messages` | 200,000 | 32,000 | yes | text, image | | `claude-opus-4-1` | Claude Opus 4.1 (latest) | `anthropic-messages` | 200,000 | 32,000 | yes | text, image | | `claude-opus-4-5` | Claude Opus 4.5 (latest) | `anthropic-messages` | 200,000 | 64,000 | yes | text, image | | `claude-opus-4-6` | Claude Opus 4.6 (latest) | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `claude-opus-4-7` | Claude Opus 4.7 | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `claude-opus-4-8` | Claude Opus 4.8 | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `claude-opus-5` | Claude Opus 5 | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `claude-sonnet-4` | Claude Sonnet 4 (latest) | `anthropic-messages` | 200,000 | 64,000 | yes | text, image | | `claude-sonnet-4-5` | Claude Sonnet 4.5 (latest) | `anthropic-messages` | 200,000 | 64,000 | yes | text, image | | `claude-sonnet-4-6` | Claude Sonnet 4.6 | `anthropic-messages` | 1,000,000 | 64,000 | yes | text, image | | `claude-sonnet-5` | Claude Sonnet 5 | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `gpt-4` | GPT-4 | `openai-responses` | 8,192 | 8,192 | no | text | | `gpt-4-turbo` | GPT-4 Turbo | `openai-responses` | 128,000 | 4,096 | no | text, image | | `gpt-4o` | GPT-4o | `openai-responses` | 128,000 | 16,384 | no | text, image | | `gpt-4o-mini` | GPT-4o mini | `openai-responses` | 128,000 | 16,384 | no | text, image | | `gpt-5.1` | GPT-5.1 | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.1-codex` | GPT-5.1 Codex | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.2` | GPT-5.2 | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.2-codex` | GPT-5.2 Codex | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.3-codex` | GPT-5.3 Codex | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.4` | GPT-5.4 | `openai-responses` | 1,050,000 | 128,000 | yes | text, image | | `gpt-5.5` | GPT-5.5 | `openai-responses` | 1,050,000 | 128,000 | yes | text, image | | `gpt-5.6-luna` | GPT-5.6 Luna | `openai-responses` | 1,050,000 | 128,000 | yes | text, image | | `gpt-5.6-sol` | GPT-5.6 Sol | `openai-responses` | 1,050,000 | 128,000 | yes | text, image | | `gpt-5.6-terra` | GPT-5.6 Terra | `openai-responses` | 1,050,000 | 128,000 | yes | text, image | | `o1` | o1 | `openai-responses` | 200,000 | 100,000 | yes | text, image | | `o3` | o3 | `openai-responses` | 200,000 | 100,000 | yes | text, image | | `o3-mini` | o3-mini | `openai-responses` | 200,000 | 100,000 | yes | text | | `o3-pro` | o3-pro | `openai-responses` | 200,000 | 100,000 | yes | text, image | | `o4-mini` | o4-mini | `openai-responses` | 200,000 | 100,000 | yes | text, image | | `workers-ai/@cf/moonshotai/kimi-k2.5` | Kimi K2.5 | `openai-completions` | 256,000 | 256,000 | yes | text, image | | `workers-ai/@cf/moonshotai/kimi-k2.6` | Kimi K2.6 | `openai-completions` | 256,000 | 256,000 | yes | text, image | | `workers-ai/@cf/nvidia/nemotron-3-120b-a12b` | Nemotron 3 Super 120B | `openai-completions` | 256,000 | 256,000 | yes | text | | `workers-ai/@cf/zai-org/glm-4.7-flash` | GLM-4.7-Flash | `openai-completions` | 131,072 | 131,072 | yes | text | | `workers-ai/@cf/zai-org/glm-5.2` | Glm 5.2 | `openai-completions` | 262,144 | 262,144 | yes | text | ## cloudflare-workers-ai | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | ---------------------------------------------- | ------------------------------- | -------------------- | ------: | ---------: | :-------: | ----------- | | `@cf/google/gemma-4-26b-a4b-it` | Gemma 4 26B A4B IT | `openai-completions` | 256,000 | 16,384 | yes | text, image | | `@cf/ibm-granite/granite-4.0-h-micro` | Granite 4.0 H Micro | `openai-completions` | 131,000 | 131,000 | no | text | | `@cf/meta/llama-3.3-70b-instruct-fp8-fast` | Llama 3.3 70B Instruct fp8 Fast | `openai-completions` | 24,000 | 24,000 | no | text | | `@cf/meta/llama-4-scout-17b-16e-instruct` | Llama 4 Scout 17B 16E Instruct | `openai-completions` | 131,000 | 16,384 | no | text, image | | `@cf/mistralai/mistral-small-3.1-24b-instruct` | Mistral Small 3.1 24B Instruct | `openai-completions` | 128,000 | 128,000 | no | text | | `@cf/moonshotai/kimi-k2.6` | Kimi K2.6 | `openai-completions` | 262,144 | 256,000 | yes | text, image | | `@cf/moonshotai/kimi-k2.7-code` | Kimi K2.7 Code | `openai-completions` | 262,144 | 262,144 | yes | text, image | | `@cf/nvidia/nemotron-3-120b-a12b` | Nemotron 3 Super 120B | `openai-completions` | 256,000 | 256,000 | yes | text | | `@cf/openai/gpt-oss-120b` | GPT OSS 120B | `openai-completions` | 128,000 | 16,384 | yes | text | | `@cf/openai/gpt-oss-20b` | GPT OSS 20B | `openai-completions` | 128,000 | 16,384 | yes | text | | `@cf/qwen/qwen3-30b-a3b-fp8` | Qwen3 30B A3b fp8 | `openai-completions` | 32,768 | 32,768 | yes | text | | `@cf/zai-org/glm-4.7-flash` | GLM-4.7-Flash | `openai-completions` | 131,072 | 131,072 | yes | text | | `@cf/zai-org/glm-5.2` | Glm 5.2 | `openai-completions` | 262,144 | 262,144 | yes | text | ## deepseek | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | ------------------- | ----------------- | -------------------- | --------: | ---------: | :-------: | ------ | | `deepseek-v4-flash` | DeepSeek V4 Flash | `openai-completions` | 1,000,000 | 384,000 | yes | text | | `deepseek-v4-pro` | DeepSeek V4 Pro | `openai-completions` | 1,000,000 | 384,000 | yes | text | ## fireworks | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | -------------------------------------------------- | ---------------------- | -------------------- | --------: | ---------: | :-------: | ----------- | | `accounts/fireworks/models/deepseek-v4-flash` | DeepSeek V4 Flash | `anthropic-messages` | 1,000,000 | 384,000 | yes | text | | `accounts/fireworks/models/deepseek-v4-flash-0731` | DeepSeek V4 Flash 0731 | `anthropic-messages` | 1,000,000 | 384,000 | yes | text | | `accounts/fireworks/models/deepseek-v4-pro` | DeepSeek V4 Pro | `anthropic-messages` | 1,000,000 | 384,000 | yes | text | | `accounts/fireworks/models/glm-5p2` | GLM 5.2 | `anthropic-messages` | 1,048,575 | 131,072 | yes | text | | `accounts/fireworks/models/gpt-oss-120b` | GPT OSS 120B | `anthropic-messages` | 131,072 | 32,768 | yes | text | | `accounts/fireworks/models/gpt-oss-20b` | GPT OSS 20B | `anthropic-messages` | 131,072 | 32,768 | yes | text | | `accounts/fireworks/models/kimi-k2p6` | Kimi K2.6 | `anthropic-messages` | 262,000 | 262,000 | yes | text, image | | `accounts/fireworks/models/kimi-k2p7-code` | Kimi K2.7 Code | `anthropic-messages` | 262,000 | 262,000 | yes | text, image | | `accounts/fireworks/models/kimi-k3` | Kimi K3 | `anthropic-messages` | 1,048,576 | 131,072 | yes | text, image | | `accounts/fireworks/models/minimax-m2p7` | MiniMax-M2.7 | `anthropic-messages` | 196,608 | 196,608 | yes | text | | `accounts/fireworks/models/minimax-m3` | MiniMax-M3 | `anthropic-messages` | 512,000 | 512,000 | yes | text, image | | `accounts/fireworks/models/qwen3p7-plus` | Qwen 3.7 Plus | `anthropic-messages` | 262,144 | 65,536 | yes | text, image | | `accounts/fireworks/routers/glm-5p2-fast` | GLM 5.2 Fast | `anthropic-messages` | 1,048,575 | 131,072 | yes | text | | `accounts/fireworks/routers/kimi-k2p6-fast` | Kimi K2.6 Fast | `anthropic-messages` | 262,000 | 262,000 | yes | text, image | | `accounts/fireworks/routers/kimi-k2p6-turbo` | Kimi K2.6 Turbo | `anthropic-messages` | 262,000 | 262,000 | yes | text, image | | `accounts/fireworks/routers/kimi-k2p7-code-fast` | Kimi K2.7 Code Fast | `anthropic-messages` | 262,000 | 262,000 | yes | text, image | | `accounts/fireworks/routers/kimi-k3-fast` | Kimi K3 Fast | `anthropic-messages` | 1,048,576 | 131,072 | yes | text, image | ## github-copilot | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | ------------------------- | -------------------------- | -------------------- | --------: | ---------: | :-------: | ----------- | | `claude-fable-5` | Claude Fable 5 | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `claude-haiku-4.5` | Claude Haiku 4.5 (latest) | `anthropic-messages` | 200,000 | 64,000 | yes | text, image | | `claude-opus-4.5` | Claude Opus 4.5 (latest) | `anthropic-messages` | 200,000 | 32,000 | yes | text, image | | `claude-opus-4.6` | Claude Opus 4.6 | `anthropic-messages` | 1,000,000 | 32,000 | yes | text, image | | `claude-opus-4.7` | Claude Opus 4.7 | `anthropic-messages` | 200,000 | 32,000 | yes | text, image | | `claude-opus-4.8` | Claude Opus 4.8 | `anthropic-messages` | 200,000 | 64,000 | yes | text, image | | `claude-opus-5` | Claude Opus 5 | `anthropic-messages` | 1,000,000 | 64,000 | yes | text, image | | `claude-sonnet-4` | Claude Sonnet 4 (latest) | `anthropic-messages` | 216,000 | 16,000 | yes | text, image | | `claude-sonnet-4.5` | Claude Sonnet 4.5 (latest) | `anthropic-messages` | 200,000 | 32,000 | yes | text, image | | `claude-sonnet-4.6` | Claude Sonnet 4.6 | `anthropic-messages` | 1,000,000 | 32,000 | yes | text, image | | `claude-sonnet-5` | Claude Sonnet 5 | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `gemini-3.1-pro-preview` | Gemini 3.1 Pro Preview | `openai-completions` | 1,000,000 | 64,000 | yes | text, image | | `gemini-3.5-flash` | Gemini 3.5 Flash | `openai-completions` | 200,000 | 64,000 | yes | text, image | | `gemini-3.6-flash` | Gemini 3.6 Flash | `openai-completions` | 1,000,000 | 64,000 | yes | text, image | | `gpt-4.1` | GPT-4.1 | `openai-completions` | 128,000 | 16,384 | no | text, image | | `gpt-5-mini` | GPT-5 Mini | `openai-responses` | 264,000 | 64,000 | yes | text, image | | `gpt-5.2` | GPT-5.2 | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.2-codex` | GPT-5.2 Codex | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.3-codex` | GPT-5.3 Codex | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.4` | GPT-5.4 | `openai-responses` | 1,050,000 | 128,000 | yes | text, image | | `gpt-5.4-mini` | GPT-5.4 mini | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.4-nano` | GPT-5.4 nano | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.5` | GPT-5.5 | `openai-responses` | 1,050,000 | 128,000 | yes | text, image | | `gpt-5.6-luna` | GPT-5.6 Luna | `openai-responses` | 1,050,000 | 128,000 | yes | text, image | | `gpt-5.6-sol` | GPT-5.6 Sol | `openai-responses` | 1,050,000 | 128,000 | yes | text, image | | `gpt-5.6-terra` | GPT-5.6 Terra | `openai-responses` | 1,050,000 | 128,000 | yes | text, image | | `grok-4.5` | Grok 4.5 | `openai-completions` | 500,000 | 128,000 | yes | text, image | | `kimi-k2.7-code` | Kimi K2.7 Code | `openai-completions` | 256,000 | 32,000 | yes | text, image | | `mai-code-1-flash-picker` | MAI-Code-1-Flash | `openai-completions` | 256,000 | 128,000 | yes | text | ## google | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | ------------------------------------ | ----------------------------------- | ---------------------- | --------: | ---------: | :-------: | ----------- | | `gemini-2.0-flash` | Gemini 2.0 Flash | `google-generative-ai` | 1,048,576 | 8,192 | no | text, image | | `gemini-2.0-flash-lite` | Gemini 2.0 Flash-Lite | `google-generative-ai` | 1,048,576 | 8,192 | no | text, image | | `gemini-2.5-flash` | Gemini 2.5 Flash | `google-generative-ai` | 1,048,576 | 65,536 | yes | text, image | | `gemini-2.5-flash-lite` | Gemini 2.5 Flash-Lite | `google-generative-ai` | 1,048,576 | 65,536 | yes | text, image | | `gemini-2.5-pro` | Gemini 2.5 Pro | `google-generative-ai` | 1,048,576 | 65,536 | yes | text, image | | `gemini-3-flash-preview` | Gemini 3 Flash Preview | `google-generative-ai` | 1,048,576 | 65,536 | yes | text, image | | `gemini-3-pro-preview` | Gemini 3 Pro Preview | `google-generative-ai` | 1,048,576 | 65,536 | yes | text, image | | `gemini-3.1-flash-lite` | Gemini 3.1 Flash Lite | `google-generative-ai` | 1,048,576 | 65,536 | yes | text, image | | `gemini-3.1-flash-lite-preview` | Gemini 3.1 Flash Lite Preview | `google-generative-ai` | 1,048,576 | 65,536 | yes | text, image | | `gemini-3.1-pro-preview` | Gemini 3.1 Pro Preview | `google-generative-ai` | 1,048,576 | 65,536 | yes | text, image | | `gemini-3.1-pro-preview-customtools` | Gemini 3.1 Pro Preview Custom Tools | `google-generative-ai` | 1,048,576 | 65,536 | yes | text, image | | `gemini-3.5-flash` | Gemini 3.5 Flash | `google-generative-ai` | 1,048,576 | 65,536 | yes | text, image | | `gemini-3.5-flash-lite` | Gemini 3.5 Flash Lite | `google-generative-ai` | 1,048,576 | 65,536 | yes | text, image | | `gemini-3.6-flash` | Gemini 3.6 Flash | `google-generative-ai` | 1,048,576 | 65,536 | yes | text, image | | `gemini-flash-latest` | Gemini Flash Latest | `google-generative-ai` | 1,048,576 | 65,536 | yes | text, image | | `gemini-flash-lite-latest` | Gemini Flash-Lite Latest | `google-generative-ai` | 1,048,576 | 65,536 | yes | text, image | | `gemini-robotics-er-1.6-preview` | Gemini Robotics-ER 1.6 Preview | `google-generative-ai` | 131,072 | 65,536 | yes | text, image | | `gemma-4-26b-a4b-it` | Gemma 4 26B A4B IT | `google-generative-ai` | 262,144 | 32,768 | yes | text, image | | `gemma-4-31b-it` | Gemma 4 31B IT | `google-generative-ai` | 262,144 | 32,768 | yes | text, image | ## google-vertex | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | --------------------------------------- | -------------------------------------------- | --------------- | --------: | ---------: | :-------: | ----------- | | `gemini-1.5-flash` | Gemini 1.5 Flash (Vertex) | `google-vertex` | 1,000,000 | 8,192 | no | text, image | | `gemini-1.5-flash-8b` | Gemini 1.5 Flash-8B (Vertex) | `google-vertex` | 1,000,000 | 8,192 | no | text, image | | `gemini-1.5-pro` | Gemini 1.5 Pro (Vertex) | `google-vertex` | 1,000,000 | 8,192 | no | text, image | | `gemini-2.0-flash` | Gemini 2.0 Flash (Vertex) | `google-vertex` | 1,048,576 | 8,192 | no | text, image | | `gemini-2.0-flash-lite` | Gemini 2.0 Flash Lite (Vertex) | `google-vertex` | 1,048,576 | 65,536 | yes | text, image | | `gemini-2.5-flash` | Gemini 2.5 Flash (Vertex) | `google-vertex` | 1,048,576 | 65,536 | yes | text, image | | `gemini-2.5-flash-lite` | Gemini 2.5 Flash Lite (Vertex) | `google-vertex` | 1,048,576 | 65,536 | yes | text, image | | `gemini-2.5-flash-lite-preview-09-2025` | Gemini 2.5 Flash Lite Preview 09-25 (Vertex) | `google-vertex` | 1,048,576 | 65,536 | yes | text, image | | `gemini-2.5-pro` | Gemini 2.5 Pro (Vertex) | `google-vertex` | 1,048,576 | 65,536 | yes | text, image | | `gemini-3-flash-preview` | Gemini 3 Flash Preview (Vertex) | `google-vertex` | 1,048,576 | 65,536 | yes | text, image | | `gemini-3-pro-preview` | Gemini 3 Pro Preview (Vertex) | `google-vertex` | 1,000,000 | 64,000 | yes | text, image | | `gemini-3.1-pro-preview` | Gemini 3.1 Pro Preview (Vertex) | `google-vertex` | 1,048,576 | 65,536 | yes | text, image | | `gemini-3.1-pro-preview-customtools` | Gemini 3.1 Pro Preview Custom Tools (Vertex) | `google-vertex` | 1,048,576 | 65,536 | yes | text, image | ## groq | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | ------------------------------ | ------------------ | -------------------- | ------: | ---------: | :-------: | ----------- | | `llama-3.1-8b-instant` | Llama 3.1 8B | `openai-completions` | 131,072 | 131,072 | no | text | | `llama-3.3-70b-versatile` | Llama 3.3 70B | `openai-completions` | 131,072 | 32,768 | no | text | | `openai/gpt-oss-120b` | GPT OSS 120B | `openai-completions` | 131,072 | 65,536 | yes | text | | `openai/gpt-oss-20b` | GPT OSS 20B | `openai-completions` | 131,072 | 65,536 | yes | text | | `openai/gpt-oss-safeguard-20b` | Safety GPT OSS 20B | `openai-completions` | 131,072 | 65,536 | yes | text | | `qwen/qwen3.6-27b` | Qwen3.6 27B | `openai-completions` | 131,072 | 16,384 | yes | text, image | ## huggingface | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | ------------------------------------- | ------------------------------ | -------------------- | --------: | ---------: | :-------: | ----------- | | `deepseek-ai/DeepSeek-R1` | DeepSeek-R1 | `openai-completions` | 64,000 | 32,768 | yes | text | | `deepseek-ai/DeepSeek-R1-0528` | DeepSeek-R1-0528 | `openai-completions` | 163,840 | 163,840 | yes | text | | `deepseek-ai/DeepSeek-V3.2` | DeepSeek-V3.2 | `openai-completions` | 163,840 | 65,536 | yes | text | | `deepseek-ai/DeepSeek-V4-Flash` | DeepSeek V4 Flash | `openai-completions` | 1,048,576 | 384,000 | yes | text | | `deepseek-ai/DeepSeek-V4-Flash-0731` | DeepSeek V4 Flash 0731 | `openai-completions` | 1,048,576 | 384,000 | yes | text | | `deepseek-ai/DeepSeek-V4-Pro` | DeepSeek V4 Pro | `openai-completions` | 1,048,576 | 393,216 | yes | text | | `google/gemma-4-26B-A4B-it` | Gemma 4 26B A4B IT | `openai-completions` | 262,144 | 32,768 | yes | text, image | | `google/gemma-4-31B-it` | Gemma 4 31B IT | `openai-completions` | 262,144 | 32,768 | yes | text, image | | `meta-llama/Llama-3.3-70B-Instruct` | Llama-3.3-70B-Instruct | `openai-completions` | 131,072 | 4,096 | no | text | | `MiniMaxAI/MiniMax-M2` | MiniMax-M2 | `openai-completions` | 204,800 | 128,000 | yes | text | | `MiniMaxAI/MiniMax-M2.1` | MiniMax-M2.1 | `openai-completions` | 204,800 | 131,072 | yes | text | | `MiniMaxAI/MiniMax-M2.5` | MiniMax-M2.5 | `openai-completions` | 204,800 | 131,072 | yes | text | | `MiniMaxAI/MiniMax-M2.7` | MiniMax-M2.7 | `openai-completions` | 204,800 | 131,072 | yes | text | | `MiniMaxAI/MiniMax-M3` | MiniMax-M3 | `openai-completions` | 524,288 | 128,000 | yes | text, image | | `moonshotai/Kimi-K2-Instruct` | Kimi-K2-Instruct | `openai-completions` | 131,072 | 16,384 | no | text | | `moonshotai/Kimi-K2-Instruct-0905` | Kimi-K2-Instruct-0905 | `openai-completions` | 262,144 | 16,384 | no | text | | `moonshotai/Kimi-K2-Thinking` | Kimi-K2-Thinking | `openai-completions` | 262,144 | 262,144 | yes | text | | `moonshotai/Kimi-K2.5` | Kimi-K2.5 | `openai-completions` | 262,144 | 262,144 | yes | text, image | | `moonshotai/Kimi-K2.6` | Kimi-K2.6 | `openai-completions` | 262,144 | 262,144 | yes | text, image | | `moonshotai/Kimi-K2.7-Code` | Kimi K2.7 Code | `openai-completions` | 262,144 | 262,144 | yes | text, image | | `moonshotai/Kimi-K3` | Kimi K3 | `openai-completions` | 1,000,000 | 131,072 | yes | text, image | | `openai/gpt-oss-120b` | GPT OSS 120B | `openai-completions` | 131,072 | 32,768 | yes | text | | `openai/gpt-oss-20b` | GPT OSS 20B | `openai-completions` | 131,072 | 32,768 | yes | text | | `Qwen/Qwen3-235B-A22B` | Qwen3 235B-A22B | `openai-completions` | 40,960 | 16,384 | yes | text | | `Qwen/Qwen3-235B-A22B-Thinking-2507` | Qwen3-235B-A22B-Thinking-2507 | `openai-completions` | 262,144 | 131,072 | yes | text | | `Qwen/Qwen3-32B` | Qwen3 32B | `openai-completions` | 131,072 | 16,384 | yes | text | | `Qwen/Qwen3-Coder-30B-A3B-Instruct` | Qwen3-Coder 30B-A3B Instruct | `openai-completions` | 262,144 | 65,536 | no | text | | `Qwen/Qwen3-Coder-480B-A35B-Instruct` | Qwen3-Coder-480B-A35B-Instruct | `openai-completions` | 262,144 | 66,536 | no | text | | `Qwen/Qwen3-Coder-Next` | Qwen3-Coder-Next | `openai-completions` | 262,144 | 65,536 | no | text | | `Qwen/Qwen3-Next-80B-A3B-Instruct` | Qwen3-Next-80B-A3B-Instruct | `openai-completions` | 262,144 | 66,536 | no | text | | `Qwen/Qwen3-Next-80B-A3B-Thinking` | Qwen3-Next-80B-A3B-Thinking | `openai-completions` | 262,144 | 131,072 | no | text | | `Qwen/Qwen3.5-122B-A10B` | Qwen3.5 122B-A10B | `openai-completions` | 262,144 | 65,536 | yes | text, image | | `Qwen/Qwen3.5-27B` | Qwen3.5 27B | `openai-completions` | 262,144 | 65,536 | yes | text, image | | `Qwen/Qwen3.5-35B-A3B` | Qwen3.5 35B-A3B | `openai-completions` | 262,144 | 65,536 | yes | text, image | | `Qwen/Qwen3.5-397B-A17B` | Qwen3.5-397B-A17B | `openai-completions` | 262,144 | 32,768 | yes | text, image | | `Qwen/Qwen3.5-9B` | Qwen3.5 9B | `openai-completions` | 262,144 | 65,536 | yes | text, image | | `Qwen/Qwen3.6-27B` | Qwen3.6 27B | `openai-completions` | 262,144 | 65,536 | yes | text, image | | `Qwen/Qwen3.6-35B-A3B` | Qwen3.6 35B-A3B | `openai-completions` | 262,144 | 65,536 | yes | text, image | | `stepfun-ai/Step-3.5-Flash` | Step 3.5 Flash | `openai-completions` | 262,144 | 256,000 | yes | text | | `stepfun-ai/Step-3.7-Flash` | Step 3.7 Flash | `openai-completions` | 262,144 | 256,000 | yes | text, image | | `tencent/Hy3` | Hy3 | `openai-completions` | 262,144 | 64,000 | yes | text | | `thinkingmachines/Inkling` | Inkling | `openai-completions` | 1,048,576 | 1,048,576 | yes | text, image | | `thinkingmachines/Inkling-Small` | Inkling Small | `openai-completions` | 524,288 | 1,048,576 | yes | text, image | | `XiaomiMiMo/MiMo-V2-Flash` | MiMo-V2-Flash | `openai-completions` | 262,144 | 4,096 | yes | text | | `XiaomiMiMo/MiMo-V2.5` | MiMo-V2.5 | `openai-completions` | 262,144 | 131,072 | yes | text | | `XiaomiMiMo/MiMo-V2.5-Pro` | MiMo-V2.5-Pro | `openai-completions` | 1,048,576 | 131,072 | yes | text | | `zai-org/GLM-4.5` | GLM-4.5 | `openai-completions` | 131,072 | 98,304 | yes | text | | `zai-org/GLM-4.5-Air` | GLM-4.5-Air | `openai-completions` | 131,072 | 98,304 | yes | text | | `zai-org/GLM-4.5V` | GLM-4.5V | `openai-completions` | 65,536 | 16,384 | yes | text, image | | `zai-org/GLM-4.6` | GLM-4.6 | `openai-completions` | 204,800 | 131,072 | yes | text | | `zai-org/GLM-4.7` | GLM-4.7 | `openai-completions` | 204,800 | 131,072 | yes | text | | `zai-org/GLM-4.7-Flash` | GLM-4.7-Flash | `openai-completions` | 200,000 | 128,000 | yes | text | | `zai-org/GLM-5` | GLM-5 | `openai-completions` | 202,752 | 131,072 | yes | text | | `zai-org/GLM-5.1` | GLM-5.1 | `openai-completions` | 202,752 | 131,072 | yes | text | | `zai-org/GLM-5.2` | GLM-5.2 | `openai-completions` | 262,144 | 131,072 | yes | text | ## kimi-coding | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | --------------------------- | ------------------------- | -------------------- | --------: | ---------: | :-------: | ----------- | | `k3` | Kimi K3 | `anthropic-messages` | 1,048,576 | 131,072 | yes | text, image | | `k3-256k` | Kimi K3-256K | `anthropic-messages` | 262,144 | 131,072 | yes | text, image | | `kimi-for-coding` | Kimi K2.7 Code | `anthropic-messages` | 262,144 | 32,768 | yes | text, image | | `kimi-for-coding-highspeed` | Kimi For Coding HighSpeed | `anthropic-messages` | 262,144 | 32,768 | yes | text, image | ## minimax | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | ------------------------ | ---------------------- | -------------------- | ------: | ---------: | :-------: | ------ | | `MiniMax-M2.7` | MiniMax-M2.7 | `anthropic-messages` | 204,800 | 131,072 | yes | text | | `MiniMax-M2.7-highspeed` | MiniMax-M2.7-highspeed | `anthropic-messages` | 204,800 | 131,072 | yes | text | ## minimax-cn | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | ------------------------ | ---------------------- | -------------------- | ------: | ---------: | :-------: | ------ | | `MiniMax-M2.7` | MiniMax-M2.7 | `anthropic-messages` | 204,800 | 131,072 | yes | text | | `MiniMax-M2.7-highspeed` | MiniMax-M2.7-highspeed | `anthropic-messages` | 204,800 | 131,072 | yes | text | ## mistral | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | -------------------------- | ------------------------- | ----------------------- | ------: | ---------: | :-------: | ----------- | | `codestral-latest` | Codestral (latest) | `mistral-conversations` | 256,000 | 4,096 | no | text | | `devstral-2512` | Devstral 2 | `mistral-conversations` | 262,144 | 262,144 | no | text | | `devstral-latest` | Devstral 2 | `mistral-conversations` | 262,144 | 262,144 | no | text | | `devstral-medium-2507` | Devstral Medium | `mistral-conversations` | 128,000 | 128,000 | no | text | | `devstral-medium-latest` | Devstral 2 (latest) | `mistral-conversations` | 262,144 | 262,144 | no | text | | `devstral-small-2505` | Devstral Small 2505 | `mistral-conversations` | 128,000 | 128,000 | no | text | | `devstral-small-2507` | Devstral Small | `mistral-conversations` | 128,000 | 128,000 | no | text | | `labs-devstral-small-2512` | Devstral Small 2 | `mistral-conversations` | 256,000 | 256,000 | no | text, image | | `magistral-medium-latest` | Magistral Medium (latest) | `mistral-conversations` | 128,000 | 16,384 | yes | text | | `magistral-small` | Magistral Small | `mistral-conversations` | 128,000 | 128,000 | yes | text | | `ministral-3b-latest` | Ministral 3B (latest) | `mistral-conversations` | 128,000 | 128,000 | no | text | | `ministral-8b-latest` | Ministral 8B (latest) | `mistral-conversations` | 128,000 | 128,000 | no | text | | `mistral-large-2411` | Mistral Large 2.1 | `mistral-conversations` | 131,072 | 16,384 | no | text | | `mistral-large-2512` | Mistral Large 3 | `mistral-conversations` | 262,144 | 262,144 | no | text, image | | `mistral-large-latest` | Mistral Large (latest) | `mistral-conversations` | 262,144 | 262,144 | no | text, image | | `mistral-medium-2505` | Mistral Medium 3 | `mistral-conversations` | 131,072 | 131,072 | no | text, image | | `mistral-medium-2508` | Mistral Medium 3.1 | `mistral-conversations` | 262,144 | 262,144 | no | text, image | | `mistral-medium-2604` | Mistral Medium 3.5 | `mistral-conversations` | 262,144 | 262,144 | yes | text, image | | `mistral-medium-3.5` | Mistral Medium 3.5 | `mistral-conversations` | 262,144 | 262,144 | yes | text, image | | `mistral-medium-latest` | Mistral Medium (latest) | `mistral-conversations` | 262,144 | 262,144 | yes | text, image | | `mistral-nemo` | Mistral Nemo | `mistral-conversations` | 128,000 | 128,000 | no | text | | `mistral-small-2506` | Mistral Small 3.2 | `mistral-conversations` | 128,000 | 16,384 | no | text, image | | `mistral-small-2603` | Mistral Small 4 | `mistral-conversations` | 256,000 | 256,000 | yes | text, image | | `mistral-small-latest` | Mistral Small (latest) | `mistral-conversations` | 256,000 | 256,000 | yes | text, image | | `open-mistral-7b` | Mistral 7B | `mistral-conversations` | 8,000 | 8,000 | no | text | | `open-mistral-nemo` | Open Mistral Nemo | `mistral-conversations` | 128,000 | 128,000 | no | text | | `open-mixtral-8x22b` | Mixtral 8x22B | `mistral-conversations` | 64,000 | 64,000 | no | text | | `open-mixtral-8x7b` | Mixtral 8x7B | `mistral-conversations` | 32,000 | 32,000 | no | text | | `pixtral-12b` | Pixtral 12B | `mistral-conversations` | 128,000 | 128,000 | no | text, image | | `pixtral-large-latest` | Pixtral Large (latest) | `mistral-conversations` | 128,000 | 128,000 | no | text, image | | `voxtral-small-latest` | Voxtral Small (latest) | `mistral-conversations` | 32,000 | 32,000 | no | text | ## moonshotai | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | -------------------------- | ------------------------ | -------------------- | --------: | ---------: | :-------: | ----------- | | `kimi-k2-0711-preview` | Kimi K2 0711 | `openai-completions` | 131,072 | 16,384 | no | text | | `kimi-k2-0905-preview` | Kimi K2 0905 | `openai-completions` | 262,144 | 262,144 | no | text | | `kimi-k2-thinking` | Kimi K2 Thinking | `openai-completions` | 262,144 | 262,144 | yes | text | | `kimi-k2-thinking-turbo` | Kimi K2 Thinking Turbo | `openai-completions` | 262,144 | 262,144 | yes | text | | `kimi-k2-turbo-preview` | Kimi K2 Turbo | `openai-completions` | 262,144 | 262,144 | no | text | | `kimi-k2.5` | Kimi K2.5 | `openai-completions` | 262,144 | 262,144 | yes | text, image | | `kimi-k2.6` | Kimi K2.6 | `openai-completions` | 262,144 | 262,144 | yes | text, image | | `kimi-k2.7-code` | Kimi K2.7 Code | `openai-completions` | 262,144 | 262,144 | yes | text, image | | `kimi-k2.7-code-highspeed` | Kimi K2.7 Code HighSpeed | `openai-completions` | 262,144 | 262,144 | yes | text, image | | `kimi-k3` | Kimi K3 | `openai-completions` | 1,048,576 | 131,072 | yes | text, image | ## moonshotai-cn | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | -------------------------- | ------------------------ | -------------------- | --------: | ---------: | :-------: | ----------- | | `kimi-k2-0711-preview` | Kimi K2 0711 | `openai-completions` | 131,072 | 16,384 | no | text | | `kimi-k2-0905-preview` | Kimi K2 0905 | `openai-completions` | 262,144 | 262,144 | no | text | | `kimi-k2-thinking` | Kimi K2 Thinking | `openai-completions` | 262,144 | 262,144 | yes | text | | `kimi-k2-thinking-turbo` | Kimi K2 Thinking Turbo | `openai-completions` | 262,144 | 262,144 | yes | text | | `kimi-k2-turbo-preview` | Kimi K2 Turbo | `openai-completions` | 262,144 | 262,144 | no | text | | `kimi-k2.5` | Kimi K2.5 | `openai-completions` | 262,144 | 262,144 | yes | text, image | | `kimi-k2.6` | Kimi K2.6 | `openai-completions` | 262,144 | 262,144 | yes | text, image | | `kimi-k2.7-code` | Kimi K2.7 Code | `openai-completions` | 262,144 | 262,144 | yes | text, image | | `kimi-k2.7-code-highspeed` | Kimi K2.7 Code HighSpeed | `openai-completions` | 262,144 | 262,144 | yes | text, image | | `kimi-k3` | Kimi K3 | `openai-completions` | 1,048,576 | 131,072 | yes | text, image | ## openai | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | --------------------- | --------------------- | ------------------ | --------: | ---------: | :-------: | ----------- | | `gpt-4` | GPT-4 | `openai-responses` | 8,192 | 8,192 | no | text | | `gpt-4-turbo` | GPT-4 Turbo | `openai-responses` | 128,000 | 4,096 | no | text, image | | `gpt-4.1` | GPT-4.1 | `openai-responses` | 1,047,576 | 32,768 | no | text, image | | `gpt-4.1-mini` | GPT-4.1 mini | `openai-responses` | 1,047,576 | 32,768 | no | text, image | | `gpt-4.1-nano` | GPT-4.1 nano | `openai-responses` | 1,047,576 | 32,768 | no | text, image | | `gpt-4o` | GPT-4o | `openai-responses` | 128,000 | 16,384 | no | text, image | | `gpt-4o-2024-05-13` | GPT-4o (2024-05-13) | `openai-responses` | 128,000 | 4,096 | no | text, image | | `gpt-4o-2024-08-06` | GPT-4o (2024-08-06) | `openai-responses` | 128,000 | 16,384 | no | text, image | | `gpt-4o-2024-11-20` | GPT-4o (2024-11-20) | `openai-responses` | 128,000 | 16,384 | no | text, image | | `gpt-4o-mini` | GPT-4o mini | `openai-responses` | 128,000 | 16,384 | no | text, image | | `gpt-5` | GPT-5 | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5-chat-latest` | GPT-5 Chat Latest | `openai-responses` | 128,000 | 16,384 | no | text, image | | `gpt-5-mini` | GPT-5 Mini | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5-nano` | GPT-5 Nano | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5-pro` | GPT-5 Pro | `openai-responses` | 400,000 | 272,000 | yes | text, image | | `gpt-5.1` | GPT-5.1 | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.1-codex` | GPT-5.1 Codex | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.1-codex-max` | GPT-5.1 Codex Max | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.2` | GPT-5.2 | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.2-chat-latest` | GPT-5.2 Chat | `openai-responses` | 128,000 | 16,384 | yes | text, image | | `gpt-5.2-pro` | GPT-5.2 Pro | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.3-chat-latest` | GPT-5.3 Chat (latest) | `openai-responses` | 128,000 | 16,384 | no | text, image | | `gpt-5.3-codex` | GPT-5.3 Codex | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.3-codex-spark` | GPT-5.3 Codex Spark | `openai-responses` | 128,000 | 32,000 | yes | text, image | | `gpt-5.4` | GPT-5.4 | `openai-responses` | 272,000 | 128,000 | yes | text, image | | `gpt-5.4-mini` | GPT-5.4 mini | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.4-nano` | GPT-5.4 nano | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.4-pro` | GPT-5.4 Pro | `openai-responses` | 1,050,000 | 128,000 | yes | text, image | | `gpt-5.5` | GPT-5.5 | `openai-responses` | 272,000 | 128,000 | yes | text, image | | `gpt-5.5-pro` | GPT-5.5 Pro | `openai-responses` | 1,050,000 | 128,000 | yes | text, image | | `gpt-5.6` | GPT-5.6 | `openai-responses` | 1,050,000 | 128,000 | yes | text, image | | `gpt-5.6-luna` | GPT-5.6 Luna | `openai-responses` | 1,050,000 | 128,000 | yes | text, image | | `gpt-5.6-sol` | GPT-5.6 Sol | `openai-responses` | 1,050,000 | 128,000 | yes | text, image | | `gpt-5.6-terra` | GPT-5.6 Terra | `openai-responses` | 1,050,000 | 128,000 | yes | text, image | | `gpt-realtime-2.1` | GPT-Realtime-2.1 | `openai-responses` | 128,000 | 32,000 | yes | text, image | | `o1` | o1 | `openai-responses` | 200,000 | 100,000 | yes | text, image | | `o1-pro` | o1-pro | `openai-responses` | 200,000 | 100,000 | yes | text, image | | `o3` | o3 | `openai-responses` | 200,000 | 100,000 | yes | text, image | | `o3-mini` | o3-mini | `openai-responses` | 200,000 | 100,000 | yes | text | | `o3-pro` | o3-pro | `openai-responses` | 200,000 | 100,000 | yes | text, image | | `o4-mini` | o4-mini | `openai-responses` | 200,000 | 100,000 | yes | text, image | ## openai-codex | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | --------------------- | ------------------- | ------------------------ | ------: | ---------: | :-------: | ----------- | | `gpt-5.1` | GPT-5.1 | `openai-codex-responses` | 272,000 | 128,000 | yes | text, image | | `gpt-5.1-codex-max` | GPT-5.1 Codex Max | `openai-codex-responses` | 272,000 | 128,000 | yes | text, image | | `gpt-5.1-codex-mini` | GPT-5.1 Codex Mini | `openai-codex-responses` | 272,000 | 128,000 | yes | text, image | | `gpt-5.2` | GPT-5.2 | `openai-codex-responses` | 272,000 | 128,000 | yes | text, image | | `gpt-5.2-codex` | GPT-5.2 Codex | `openai-codex-responses` | 272,000 | 128,000 | yes | text, image | | `gpt-5.3-codex` | GPT-5.3 Codex | `openai-codex-responses` | 272,000 | 128,000 | yes | text, image | | `gpt-5.3-codex-spark` | GPT-5.3 Codex Spark | `openai-codex-responses` | 128,000 | 128,000 | yes | text | | `gpt-5.4` | GPT-5.4 | `openai-codex-responses` | 272,000 | 128,000 | yes | text, image | | `gpt-5.4-mini` | GPT-5.4 Mini | `openai-codex-responses` | 272,000 | 128,000 | yes | text, image | | `gpt-5.5` | GPT-5.5 | `openai-codex-responses` | 272,000 | 128,000 | yes | text, image | | `gpt-5.6-luna` | GPT-5.6 Luna | `openai-codex-responses` | 272,000 | 128,000 | yes | text, image | | `gpt-5.6-sol` | GPT-5.6 Sol | `openai-codex-responses` | 272,000 | 128,000 | yes | text, image | | `gpt-5.6-terra` | GPT-5.6 Terra | `openai-codex-responses` | 272,000 | 128,000 | yes | text, image | ## opencode | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | ------------------------ | ---------------------------- | ---------------------- | --------: | ---------: | :-------: | ----------- | | `big-pickle` | Big Pickle | `openai-completions` | 200,000 | 32,000 | yes | text | | `claude-fable-5` | Claude Fable 5 | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `claude-haiku-4-5` | Claude Haiku 4.5 | `anthropic-messages` | 200,000 | 64,000 | yes | text, image | | `claude-opus-4-1` | Claude Opus 4.1 | `anthropic-messages` | 200,000 | 32,000 | yes | text, image | | `claude-opus-4-5` | Claude Opus 4.5 | `anthropic-messages` | 200,000 | 64,000 | yes | text, image | | `claude-opus-4-6` | Claude Opus 4.6 | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `claude-opus-4-7` | Claude Opus 4.7 | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `claude-opus-4-8` | Claude Opus 4.8 | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `claude-opus-5` | Claude Opus 5 | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `claude-sonnet-4` | Claude Sonnet 4 | `anthropic-messages` | 200,000 | 64,000 | yes | text, image | | `claude-sonnet-4-5` | Claude Sonnet 4.5 | `anthropic-messages` | 200,000 | 64,000 | yes | text, image | | `claude-sonnet-4-6` | Claude Sonnet 4.6 | `anthropic-messages` | 1,000,000 | 64,000 | yes | text, image | | `claude-sonnet-5` | Claude Sonnet 5 | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `deepseek-v4-flash` | DeepSeek V4 Flash (New) | `openai-completions` | 1,000,000 | 384,000 | yes | text | | `deepseek-v4-flash-free` | DeepSeek V4 Flash Free (New) | `openai-completions` | 200,000 | 128,000 | yes | text | | `deepseek-v4-pro` | DeepSeek V4 Pro | `openai-completions` | 1,000,000 | 384,000 | yes | text | | `gemini-3-flash` | Gemini 3 Flash | `google-generative-ai` | 1,048,576 | 65,536 | yes | text, image | | `gemini-3.1-pro` | Gemini 3.1 Pro Preview | `google-generative-ai` | 1,048,576 | 65,536 | yes | text, image | | `gemini-3.5-flash` | Gemini 3.5 Flash | `google-generative-ai` | 1,048,576 | 65,536 | yes | text, image | | `gemini-3.5-flash-lite` | Gemini 3.5 Flash Lite | `google-generative-ai` | 1,048,576 | 65,536 | yes | text, image | | `gemini-3.6-flash` | Gemini 3.6 Flash | `google-generative-ai` | 1,048,576 | 65,536 | yes | text, image | | `glm-5` | GLM-5 | `openai-completions` | 204,800 | 131,072 | yes | text | | `glm-5.1` | GLM-5.1 | `openai-completions` | 204,800 | 131,072 | yes | text | | `glm-5.2` | GLM-5.2 | `openai-completions` | 1,000,000 | 131,072 | yes | text | | `gpt-5` | GPT-5 | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5-codex` | GPT-5 Codex | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5-nano` | GPT-5 Nano | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.1` | GPT-5.1 | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.1-codex` | GPT-5.1 Codex | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.1-codex-max` | GPT-5.1 Codex Max | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.1-codex-mini` | GPT-5.1 Codex Mini | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.2` | GPT-5.2 | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.2-codex` | GPT-5.2 Codex | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.3-codex` | GPT-5.3 Codex | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.4` | GPT-5.4 | `openai-responses` | 272,000 | 128,000 | yes | text, image | | `gpt-5.4-mini` | GPT-5.4 Mini | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.4-nano` | GPT-5.4 Nano | `openai-responses` | 400,000 | 128,000 | yes | text, image | | `gpt-5.4-pro` | GPT-5.4 Pro | `openai-responses` | 1,050,000 | 128,000 | yes | text, image | | `gpt-5.5` | GPT-5.5 | `openai-responses` | 1,050,000 | 128,000 | yes | text, image | | `gpt-5.5-pro` | GPT-5.5 Pro | `openai-responses` | 1,050,000 | 128,000 | yes | text, image | | `gpt-5.6-luna` | GPT-5.6 Luna | `openai-responses` | 1,050,000 | 128,000 | yes | text, image | | `gpt-5.6-sol` | GPT-5.6 Sol | `openai-responses` | 1,050,000 | 128,000 | yes | text, image | | `gpt-5.6-terra` | GPT-5.6 Terra | `openai-responses` | 1,050,000 | 128,000 | yes | text, image | | `grok-4.5` | Grok 4.5 | `openai-responses` | 500,000 | 500,000 | yes | text, image | | `grok-build-0.1` | Grok Build 0.1 | `openai-completions` | 256,000 | 256,000 | yes | text, image | | `kimi-k2.5` | Kimi K2.5 | `openai-completions` | 262,144 | 65,536 | yes | text, image | | `kimi-k2.6` | Kimi K2.6 | `openai-completions` | 262,144 | 65,536 | yes | text, image | | `kimi-k2.7-code` | Kimi K2.7 Code | `openai-completions` | 262,144 | 262,144 | yes | text, image | | `kimi-k3` | Kimi K3 | `openai-completions` | 1,048,576 | 131,072 | yes | text, image | | `laguna-s-2.1-free` | Laguna S 2.1 Free | `openai-completions` | 256,000 | 32,000 | yes | text | | `ling-3.0-flash-free` | Ling-3.0-flash Free | `openai-completions` | 262,144 | 32,768 | yes | text | | `longcat-2.0-free` | LongCat-2.0 Free | `openai-completions` | 1,000,000 | 131,072 | yes | text | | `mimo-v2.5-free` | MiMo V2.5 Free | `openai-completions` | 200,000 | 32,000 | yes | text, image | | `minimax-m2.5` | MiniMax-M2.5 | `openai-completions` | 204,800 | 131,072 | yes | text | | `minimax-m2.7` | MiniMax-M2.7 | `openai-completions` | 204,800 | 131,072 | yes | text | | `minimax-m3` | MiniMax-M3 | `openai-completions` | 512,000 | 128,000 | yes | text, image | | `nemotron-3-ultra-free` | Nemotron 3 Ultra Free | `openai-completions` | 1,000,000 | 128,000 | yes | text | | `north-mini-code-free` | North Mini Code Free | `openai-completions` | 256,000 | 64,000 | yes | text | | `qwen3.5-plus` | Qwen3.5 Plus | `anthropic-messages` | 262,144 | 65,536 | yes | text, image | | `qwen3.6-plus` | Qwen3.6 Plus | `anthropic-messages` | 262,144 | 65,536 | yes | text, image | ## opencode-go | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | ------------------- | ----------------------- | -------------------- | --------: | ---------: | :-------: | ----------- | | `deepseek-v4-flash` | DeepSeek V4 Flash (New) | `openai-completions` | 1,000,000 | 384,000 | yes | text | | `deepseek-v4-pro` | DeepSeek V4 Pro | `openai-completions` | 1,000,000 | 384,000 | yes | text | | `glm-5.1` | GLM-5.1 | `openai-completions` | 202,752 | 32,768 | yes | text | | `glm-5.2` | GLM-5.2 | `openai-completions` | 1,000,000 | 131,072 | yes | text | | `gpt-5.6-luna` | GPT-5.6 Luna (2x usage) | `openai-responses` | 1,050,000 | 128,000 | yes | text, image | | `grok-4.5` | Grok 4.5 | `openai-responses` | 500,000 | 500,000 | yes | text, image | | `hy3` | Hy3 | `openai-completions` | 256,000 | 64,000 | yes | text | | `kimi-k2.6` | Kimi K2.6 | `openai-completions` | 262,144 | 65,536 | yes | text, image | | `kimi-k2.7-code` | Kimi K2.7 Code | `openai-completions` | 262,144 | 262,144 | yes | text, image | | `kimi-k3` | Kimi K3 | `openai-completions` | 1,048,576 | 131,072 | yes | text, image | | `mimo-v2.5` | MiMo V2.5 | `openai-completions` | 1,000,000 | 128,000 | yes | text, image | | `mimo-v2.5-pro` | MiMo V2.5 Pro | `openai-completions` | 1,048,576 | 128,000 | yes | text | | `minimax-m2.7` | MiniMax-M2.7 | `openai-completions` | 204,800 | 131,072 | yes | text | | `minimax-m3` | MiniMax-M3 | `anthropic-messages` | 1,000,000 | 131,072 | yes | text, image | | `qwen3.6-plus` | Qwen3.6 Plus | `openai-completions` | 1,000,000 | 65,536 | yes | text, image | | `qwen3.7-max` | Qwen3.7 Max | `anthropic-messages` | 1,000,000 | 65,536 | yes | text | | `qwen3.7-plus` | Qwen3.7 Plus | `anthropic-messages` | 1,000,000 | 65,536 | yes | text, image | | `qwen3.8-max` | Qwen3.8 Max | `anthropic-messages` | 1,000,000 | 131,072 | yes | text, image | ## openrouter | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | ---------------------------------------------------- | -------------------------------------------- | -------------------- | --------: | ---------: | :-------: | ----------- | | `~anthropic/claude-fable-latest` | Anthropic: Claude Fable Latest | `openai-completions` | 1,000,000 | 128,000 | yes | text, image | | `~anthropic/claude-haiku-latest` | Anthropic Claude Haiku Latest | `openai-completions` | 200,000 | 64,000 | yes | text, image | | `~anthropic/claude-opus-latest` | Anthropic: Claude Opus Latest | `openai-completions` | 1,000,000 | 128,000 | yes | text, image | | `~anthropic/claude-sonnet-latest` | Anthropic Claude Sonnet Latest | `openai-completions` | 1,000,000 | 128,000 | yes | text, image | | `~deepseek/deepseek-v4-flash-latest` | DeepSeek V4 Flash Latest | `openai-completions` | 1,048,576 | 65,536 | yes | text | | `~google/gemini-flash-latest` | Google Gemini Flash Latest | `openai-completions` | 1,048,576 | 65,536 | yes | text, image | | `~google/gemini-pro-latest` | Google Gemini Pro Latest | `openai-completions` | 1,048,576 | 65,536 | yes | text, image | | `~moonshotai/kimi-latest` | MoonshotAI Kimi Latest | `openai-completions` | 1,048,576 | 1,048,576 | yes | text, image | | `~openai/gpt-latest` | OpenAI GPT Latest | `openai-completions` | 1,050,000 | 128,000 | yes | text, image | | `~openai/gpt-mini-latest` | OpenAI GPT Mini Latest | `openai-completions` | 400,000 | 128,000 | yes | text, image | | `~x-ai/grok-latest` | xAI: Grok Latest | `openai-completions` | 500,000 | 4,096 | yes | text, image | | `ai21/jamba-large-1.7` | AI21: Jamba Large 1.7 | `openai-completions` | 256,000 | 4,096 | no | text | | `aion-labs/aion-2.0` | AionLabs: Aion-2.0 | `openai-completions` | 131,072 | 32,768 | yes | text | | `aion-labs/aion-3.0` | AionLabs: Aion-3.0 | `openai-completions` | 131,072 | 32,768 | yes | text | | `aion-labs/aion-3.0-mini` | AionLabs: Aion-3.0-Mini | `openai-completions` | 131,072 | 32,768 | yes | text | | `amazon/nova-2-lite-v1` | Amazon: Nova 2 Lite | `openai-completions` | 1,000,000 | 65,535 | yes | text, image | | `amazon/nova-lite-v1` | Amazon: Nova Lite 1.0 | `openai-completions` | 300,000 | 5,120 | no | text, image | | `amazon/nova-micro-v1` | Amazon: Nova Micro 1.0 | `openai-completions` | 128,000 | 5,120 | no | text | | `amazon/nova-premier-v1` | Amazon: Nova Premier 1.0 | `openai-completions` | 1,000,000 | 32,000 | no | text, image | | `amazon/nova-pro-v1` | Amazon: Nova Pro 1.0 | `openai-completions` | 300,000 | 5,120 | no | text, image | | `anthropic/claude-3-haiku` | Anthropic: Claude 3 Haiku | `openai-completions` | 200,000 | 4,096 | no | text, image | | `anthropic/claude-fable-5` | Anthropic: Claude Fable 5 | `openai-completions` | 1,000,000 | 128,000 | yes | text, image | | `anthropic/claude-haiku-4.5` | Anthropic: Claude Haiku 4.5 | `openai-completions` | 200,000 | 64,000 | yes | text, image | | `anthropic/claude-opus-4` | Anthropic: Claude Opus 4 | `openai-completions` | 200,000 | 32,000 | yes | text, image | | `anthropic/claude-opus-4.1` | Anthropic: Claude Opus 4.1 | `openai-completions` | 200,000 | 32,000 | yes | text, image | | `anthropic/claude-opus-4.5` | Anthropic: Claude Opus 4.5 | `openai-completions` | 200,000 | 64,000 | yes | text, image | | `anthropic/claude-opus-4.6` | Anthropic: Claude Opus 4.6 | `openai-completions` | 1,000,000 | 128,000 | yes | text, image | | `anthropic/claude-opus-4.7` | Anthropic: Claude Opus 4.7 | `openai-completions` | 1,000,000 | 128,000 | yes | text, image | | `anthropic/claude-opus-4.7-fast` | Anthropic: Claude Opus 4.7 (Fast) | `openai-completions` | 1,000,000 | 128,000 | yes | text, image | | `anthropic/claude-opus-4.8` | Anthropic: Claude Opus 4.8 | `openai-completions` | 1,000,000 | 128,000 | yes | text, image | | `anthropic/claude-opus-4.8-fast` | Anthropic: Claude Opus 4.8 (Fast) | `openai-completions` | 1,000,000 | 128,000 | yes | text, image | | `anthropic/claude-opus-5` | Claude Opus 5 | `openai-completions` | 1,000,000 | 128,000 | yes | text, image | | `anthropic/claude-opus-5-fast` | Claude Opus 5 (Fast) | `openai-completions` | 1,000,000 | 128,000 | yes | text, image | | `anthropic/claude-sonnet-4` | Anthropic: Claude Sonnet 4 | `openai-completions` | 1,000,000 | 64,000 | yes | text, image | | `anthropic/claude-sonnet-4.5` | Anthropic: Claude Sonnet 4.5 | `openai-completions` | 1,000,000 | 64,000 | yes | text, image | | `anthropic/claude-sonnet-4.6` | Anthropic: Claude Sonnet 4.6 | `openai-completions` | 1,000,000 | 128,000 | yes | text, image | | `anthropic/claude-sonnet-5` | Anthropic: Claude Sonnet 5 | `openai-completions` | 1,000,000 | 128,000 | yes | text, image | | `arcee-ai/trinity-large-thinking` | Arcee AI: Trinity Large Thinking | `openai-completions` | 262,144 | 262,144 | yes | text | | `arcee-ai/virtuoso-large` | Arcee AI: Virtuoso Large | `openai-completions` | 131,072 | 64,000 | no | text | | `auto` | Auto | `openai-completions` | 2,000,000 | 30,000 | yes | text, image | | `bytedance-seed/seed-1.6` | ByteDance Seed: Seed 1.6 | `openai-completions` | 262,144 | 32,768 | yes | text, image | | `bytedance-seed/seed-1.6-flash` | ByteDance Seed: Seed 1.6 Flash | `openai-completions` | 262,144 | 32,768 | yes | text, image | | `bytedance-seed/seed-2.0-lite` | ByteDance Seed: Seed-2.0-Lite | `openai-completions` | 262,144 | 131,072 | yes | text, image | | `bytedance-seed/seed-2.0-mini` | ByteDance Seed: Seed-2.0-Mini | `openai-completions` | 262,144 | 131,072 | yes | text, image | | `cohere/command-r-08-2024` | Cohere: Command R (08-2024) | `openai-completions` | 128,000 | 4,000 | no | text | | `cohere/command-r-plus-08-2024` | Cohere: Command R+ (08-2024) | `openai-completions` | 128,000 | 4,000 | no | text | | `cohere/north-mini-code:free` | Cohere: North Mini Code (free) | `openai-completions` | 256,000 | 64,000 | yes | text | | `deepseek/deepseek-chat` | DeepSeek: DeepSeek V3 | `openai-completions` | 163,840 | 16,000 | no | text | | `deepseek/deepseek-chat-v3-0324` | DeepSeek: DeepSeek V3 0324 | `openai-completions` | 163,840 | 65,536 | no | text | | `deepseek/deepseek-chat-v3.1` | DeepSeek: DeepSeek V3.1 | `openai-completions` | 163,840 | 32,768 | yes | text | | `deepseek/deepseek-r1` | DeepSeek: R1 | `openai-completions` | 163,840 | 16,000 | yes | text | | `deepseek/deepseek-r1-0528` | DeepSeek: R1 0528 | `openai-completions` | 163,840 | 32,768 | yes | text | | `deepseek/deepseek-v3.1-terminus` | DeepSeek: DeepSeek V3.1 Terminus | `openai-completions` | 163,840 | 32,768 | yes | text | | `deepseek/deepseek-v3.2` | DeepSeek: DeepSeek V3.2 | `openai-completions` | 163,840 | 65,536 | yes | text | | `deepseek/deepseek-v3.2-exp` | DeepSeek: DeepSeek V3.2 Exp | `openai-completions` | 163,840 | 65,536 | yes | text | | `deepseek/deepseek-v4-flash` | DeepSeek: DeepSeek V4 Flash 0423 | `openai-completions` | 1,048,576 | 393,216 | yes | text | | `deepseek/deepseek-v4-flash-0731` | DeepSeek: DeepSeek V4 Flash 0731 | `openai-completions` | 1,048,576 | 65,536 | yes | text | | `deepseek/deepseek-v4-pro` | DeepSeek: DeepSeek V4 Pro | `openai-completions` | 1,048,576 | 384,000 | yes | text | | `google/gemini-2.5-flash` | Google: Gemini 2.5 Flash | `openai-completions` | 1,048,576 | 65,535 | yes | text, image | | `google/gemini-2.5-flash-lite` | Google: Gemini 2.5 Flash Lite | `openai-completions` | 1,048,576 | 65,535 | yes | text, image | | `google/gemini-2.5-pro` | Google: Gemini 2.5 Pro | `openai-completions` | 1,048,576 | 65,536 | yes | text, image | | `google/gemini-2.5-pro-preview` | Google: Gemini 2.5 Pro Preview 06-05 | `openai-completions` | 1,048,576 | 65,536 | yes | text, image | | `google/gemini-2.5-pro-preview-05-06` | Google: Gemini 2.5 Pro Preview 05-06 | `openai-completions` | 1,048,576 | 65,535 | yes | text, image | | `google/gemini-3-flash-preview` | Google: Gemini 3 Flash Preview | `openai-completions` | 1,048,576 | 65,535 | yes | text, image | | `google/gemini-3-pro-image` | Google: Nano Banana Pro (Gemini 3 Pro Image) | `openai-completions` | 131,072 | 32,768 | yes | text, image | | `google/gemini-3.1-flash-lite` | Google: Gemini 3.1 Flash Lite | `openai-completions` | 1,048,576 | 65,536 | yes | text, image | | `google/gemini-3.1-flash-lite-preview` | Google: Gemini 3.1 Flash Lite Preview | `openai-completions` | 1,048,576 | 65,536 | yes | text, image | | `google/gemini-3.1-pro-preview` | Google: Gemini 3.1 Pro Preview | `openai-completions` | 1,048,576 | 65,536 | yes | text, image | | `google/gemini-3.1-pro-preview-customtools` | Google: Gemini 3.1 Pro Preview Custom Tools | `openai-completions` | 1,048,576 | 65,536 | yes | text, image | | `google/gemini-3.5-flash` | Google: Gemini 3.5 Flash | `openai-completions` | 1,048,576 | 65,536 | yes | text, image | | `google/gemini-3.5-flash-lite` | Google: Gemini 3.5 Flash Lite | `openai-completions` | 1,048,576 | 65,536 | yes | text, image | | `google/gemini-3.6-flash` | Google: Gemini 3.6 Flash | `openai-completions` | 1,048,576 | 65,536 | yes | text, image | | `google/gemma-3-12b-it` | Google: Gemma 3 12B | `openai-completions` | 131,072 | 16,384 | no | text, image | | `google/gemma-3-27b-it` | Google: Gemma 3 27B | `openai-completions` | 262,144 | 131,072 | no | text, image | | `google/gemma-4-26b-a4b-it` | Google: Gemma 4 26B A4B | `openai-completions` | 262,144 | 16,384 | yes | text, image | | `google/gemma-4-26b-a4b-it:free` | Google: Gemma 4 26B A4B (free) | `openai-completions` | 262,144 | 32,768 | yes | text, image | | `google/gemma-4-31b-it` | Google: Gemma 4 31B | `openai-completions` | 262,144 | 262,144 | yes | text, image | | `google/gemma-4-31b-it:free` | Google: Gemma 4 31B (free) | `openai-completions` | 262,144 | 32,768 | yes | text, image | | `ibm-granite/granite-4.1-8b` | IBM: Granite 4.1 8B | `openai-completions` | 131,072 | 131,072 | no | text | | `inception/mercury-2` | Inception: Mercury 2 | `openai-completions` | 128,000 | 50,000 | yes | text | | `inclusionai/ling-2.6-1t` | inclusionAI: Ling-2.6-1T | `openai-completions` | 262,144 | 32,768 | no | text | | `inclusionai/ling-2.6-flash` | inclusionAI: Ling-2.6-flash | `openai-completions` | 262,144 | 32,768 | no | text | | `inclusionai/ling-3.0-flash:free` | Ling-3.0-flash (free) | `openai-completions` | 262,144 | 32,768 | yes | text | | `inclusionai/ring-2.6-1t` | inclusionAI: Ring-2.6-1T | `openai-completions` | 262,144 | 65,536 | yes | text | | `kwaipilot/kat-coder-air-v2.5` | Kwaipilot: KAT-Coder-Air V2.5 | `openai-completions` | 256,000 | 80,000 | no | text | | `kwaipilot/kat-coder-pro-v2` | Kwaipilot: KAT-Coder-Pro V2 | `openai-completions` | 262,144 | 80,000 | no | text | | `kwaipilot/kat-coder-pro-v2.5` | Kwaipilot: KAT-Coder-Pro V2.5 | `openai-completions` | 256,000 | 80,000 | no | text | | `meituan/longcat-2.0` | Meituan: LongCat 2.0 | `openai-completions` | 1,048,756 | 262,144 | yes | text | | `meta-llama/llama-3.1-70b-instruct` | Meta: Llama 3.1 70B Instruct | `openai-completions` | 131,072 | 16,384 | no | text | | `meta-llama/llama-3.1-8b-instruct` | Meta: Llama 3.1 8B Instruct | `openai-completions` | 131,072 | 131,072 | no | text | | `meta-llama/llama-3.3-70b-instruct` | Meta: Llama 3.3 70B Instruct | `openai-completions` | 131,072 | 16,384 | no | text | | `meta-llama/llama-4-maverick` | Meta: Llama 4 Maverick | `openai-completions` | 1,048,576 | 16,384 | no | text, image | | `meta-llama/llama-4-scout` | Meta: Llama 4 Scout | `openai-completions` | 1,310,720 | 16,384 | no | text, image | | `meta/muse-spark-1.1` | Meta: Muse Spark 1.1 | `openai-completions` | 1,048,576 | 4,096 | yes | text, image | | `minimax/minimax-m1` | MiniMax: MiniMax M1 | `openai-completions` | 1,000,000 | 40,000 | yes | text | | `minimax/minimax-m2` | MiniMax: MiniMax M2 | `openai-completions` | 204,800 | 131,072 | yes | text | | `minimax/minimax-m2.1` | MiniMax: MiniMax M2.1 | `openai-completions` | 204,800 | 131,072 | yes | text | | `minimax/minimax-m2.5` | MiniMax: MiniMax M2.5 | `openai-completions` | 204,800 | 196,608 | yes | text | | `minimax/minimax-m2.7` | MiniMax: MiniMax M2.7 | `openai-completions` | 204,800 | 131,072 | yes | text | | `minimax/minimax-m3` | MiniMax: MiniMax M3 | `openai-completions` | 1,048,576 | 512,000 | yes | text, image | | `mistralai/codestral-2508` | Mistral: Codestral 2508 | `openai-completions` | 256,000 | 4,096 | no | text | | `mistralai/ministral-14b-2512` | Mistral: Ministral 3 14B 2512 | `openai-completions` | 262,144 | 4,096 | no | text, image | | `mistralai/ministral-3b-2512` | Mistral: Ministral 3 3B 2512 | `openai-completions` | 131,072 | 4,096 | no | text, image | | `mistralai/ministral-8b-2512` | Mistral: Ministral 3 8B 2512 | `openai-completions` | 262,144 | 4,096 | no | text, image | | `mistralai/mistral-large` | Mistral Large | `openai-completions` | 128,000 | 4,096 | no | text | | `mistralai/mistral-large-2407` | Mistral Large 2407 | `openai-completions` | 131,072 | 4,096 | no | text | | `mistralai/mistral-large-2512` | Mistral: Mistral Large 3 2512 | `openai-completions` | 262,144 | 4,096 | no | text, image | | `mistralai/mistral-medium-3` | Mistral: Mistral Medium 3 | `openai-completions` | 131,072 | 4,096 | no | text, image | | `mistralai/mistral-medium-3-5` | Mistral: Mistral Medium 3.5 | `openai-completions` | 262,144 | 4,096 | yes | text, image | | `mistralai/mistral-medium-3.1` | Mistral: Mistral Medium 3.1 | `openai-completions` | 131,072 | 4,096 | no | text, image | | `mistralai/mistral-nemo` | Mistral: Mistral Nemo | `openai-completions` | 131,072 | 16,384 | no | text | | `mistralai/mistral-saba` | Mistral: Saba | `openai-completions` | 32,768 | 4,096 | no | text | | `mistralai/mistral-small-2603` | Mistral: Mistral Small 4 | `openai-completions` | 262,144 | 4,096 | yes | text, image | | `mistralai/mistral-small-3.2-24b-instruct` | Mistral: Mistral Small 3.2 24B | `openai-completions` | 256,000 | 16,384 | no | text, image | | `mistralai/mixtral-8x22b-instruct` | Mistral: Mixtral 8x22B Instruct | `openai-completions` | 65,536 | 4,096 | no | text | | `mistralai/voxtral-small-24b-2507` | Mistral: Voxtral Small 24B 2507 | `openai-completions` | 32,000 | 4,096 | no | text | | `moonshotai/kimi-k2` | MoonshotAI: Kimi K2 0711 | `openai-completions` | 131,072 | 100,352 | no | text | | `moonshotai/kimi-k2-0905` | MoonshotAI: Kimi K2 0905 | `openai-completions` | 262,144 | 100,352 | no | text | | `moonshotai/kimi-k2-thinking` | MoonshotAI: Kimi K2 Thinking | `openai-completions` | 262,144 | 100,352 | yes | text | | `moonshotai/kimi-k2.5` | MoonshotAI: Kimi K2.5 | `openai-completions` | 262,144 | 4,096 | yes | text, image | | `moonshotai/kimi-k2.6` | MoonshotAI: Kimi K2.6 | `openai-completions` | 262,144 | 262,144 | yes | text, image | | `moonshotai/kimi-k2.7-code` | MoonshotAI: Kimi K2.7 Code | `openai-completions` | 262,144 | 262,144 | yes | text, image | | `moonshotai/kimi-k3` | MoonshotAI: Kimi K3 | `openai-completions` | 1,048,576 | 1,048,576 | yes | text, image | | `nex-agi/nex-n2-mini` | Nex AGI: Nex-N2-Mini | `openai-completions` | 262,144 | 262,144 | yes | text, image | | `nex-agi/nex-n2-pro` | Nex AGI: Nex-N2-Pro | `openai-completions` | 262,144 | 262,144 | yes | text, image | | `nvidia/nemotron-3-nano-30b-a3b` | NVIDIA: Nemotron 3 Nano 30B A3B | `openai-completions` | 262,144 | 262,144 | yes | text | | `nvidia/nemotron-3-nano-30b-a3b:free` | NVIDIA: Nemotron 3 Nano 30B A3B (free) | `openai-completions` | 256,000 | 4,096 | yes | text | | `nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free` | NVIDIA: Nemotron 3 Nano Omni (free) | `openai-completions` | 256,000 | 65,536 | yes | text, image | | `nvidia/nemotron-3-super-120b-a12b` | NVIDIA: Nemotron 3 Super | `openai-completions` | 1,000,000 | 16,384 | yes | text | | `nvidia/nemotron-3-super-120b-a12b:free` | NVIDIA: Nemotron 3 Super (free) | `openai-completions` | 262,144 | 262,144 | yes | text | | `nvidia/nemotron-3-ultra-550b-a55b` | NVIDIA: Nemotron 3 Ultra | `openai-completions` | 512,288 | 4,096 | yes | text | | `nvidia/nemotron-3-ultra-550b-a55b:free` | NVIDIA: Nemotron 3 Ultra (free) | `openai-completions` | 1,000,000 | 65,536 | yes | text | | `nvidia/nemotron-nano-12b-v2-vl:free` | NVIDIA: Nemotron Nano 12B 2 VL (free) | `openai-completions` | 128,000 | 128,000 | yes | text, image | | `nvidia/nemotron-nano-9b-v2:free` | NVIDIA: Nemotron Nano 9B V2 (free) | `openai-completions` | 128,000 | 4,096 | yes | text | | `openai/gpt-3.5-turbo` | OpenAI: GPT-3.5 Turbo | `openai-completions` | 16,385 | 4,096 | no | text | | `openai/gpt-3.5-turbo-0613` | OpenAI: GPT-3.5 Turbo (older v0613) | `openai-completions` | 4,095 | 4,096 | no | text | | `openai/gpt-3.5-turbo-16k` | OpenAI: GPT-3.5 Turbo 16k | `openai-completions` | 16,385 | 4,096 | no | text | | `openai/gpt-4` | OpenAI: GPT-4 | `openai-completions` | 8,191 | 4,096 | no | text | | `openai/gpt-4-turbo` | OpenAI: GPT-4 Turbo | `openai-completions` | 128,000 | 4,096 | no | text, image | | `openai/gpt-4-turbo-preview` | OpenAI: GPT-4 Turbo Preview | `openai-completions` | 128,000 | 4,096 | no | text | | `openai/gpt-4.1` | OpenAI: GPT-4.1 | `openai-completions` | 1,047,576 | 32,768 | no | text, image | | `openai/gpt-4.1-mini` | OpenAI: GPT-4.1 Mini | `openai-completions` | 1,047,576 | 32,768 | no | text, image | | `openai/gpt-4.1-nano` | OpenAI: GPT-4.1 Nano | `openai-completions` | 1,047,576 | 32,768 | no | text, image | | `openai/gpt-4o` | OpenAI: GPT-4o | `openai-completions` | 128,000 | 16,384 | no | text, image | | `openai/gpt-4o-2024-05-13` | OpenAI: GPT-4o (2024-05-13) | `openai-completions` | 128,000 | 4,096 | no | text, image | | `openai/gpt-4o-2024-08-06` | OpenAI: GPT-4o (2024-08-06) | `openai-completions` | 128,000 | 16,384 | no | text, image | | `openai/gpt-4o-2024-11-20` | OpenAI: GPT-4o (2024-11-20) | `openai-completions` | 128,000 | 16,384 | no | text, image | | `openai/gpt-4o-mini` | OpenAI: GPT-4o-mini | `openai-completions` | 128,000 | 16,384 | no | text, image | | `openai/gpt-4o-mini-2024-07-18` | OpenAI: GPT-4o-mini (2024-07-18) | `openai-completions` | 128,000 | 16,384 | no | text, image | | `openai/gpt-5` | OpenAI: GPT-5 | `openai-completions` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5-mini` | OpenAI: GPT-5 Mini | `openai-completions` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5-nano` | OpenAI: GPT-5 Nano | `openai-completions` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5-pro` | OpenAI: GPT-5 Pro | `openai-completions` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5.1` | OpenAI: GPT-5.1 | `openai-completions` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5.1-codex` | OpenAI: GPT-5.1-Codex | `openai-completions` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5.1-codex-max` | OpenAI: GPT-5.1-Codex-Max | `openai-completions` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5.1-codex-mini` | OpenAI: GPT-5.1-Codex-Mini | `openai-completions` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5.2` | OpenAI: GPT-5.2 | `openai-completions` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5.2-chat` | OpenAI: GPT-5.2 Chat | `openai-completions` | 128,000 | 16,384 | no | text, image | | `openai/gpt-5.2-codex` | OpenAI: GPT-5.2-Codex | `openai-completions` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5.2-pro` | OpenAI: GPT-5.2 Pro | `openai-completions` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5.3-chat` | OpenAI: GPT-5.3 Chat | `openai-completions` | 128,000 | 16,384 | no | text, image | | `openai/gpt-5.3-codex` | OpenAI: GPT-5.3-Codex | `openai-completions` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5.4` | OpenAI: GPT-5.4 | `openai-completions` | 1,050,000 | 128,000 | yes | text, image | | `openai/gpt-5.4-mini` | OpenAI: GPT-5.4 Mini | `openai-completions` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5.4-nano` | OpenAI: GPT-5.4 Nano | `openai-completions` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5.4-pro` | OpenAI: GPT-5.4 Pro | `openai-completions` | 1,050,000 | 128,000 | yes | text, image | | `openai/gpt-5.5` | OpenAI: GPT-5.5 | `openai-completions` | 1,050,000 | 128,000 | yes | text, image | | `openai/gpt-5.5-pro` | OpenAI: GPT-5.5 Pro | `openai-completions` | 1,050,000 | 128,000 | yes | text, image | | `openai/gpt-5.6-luna` | OpenAI: GPT-5.6 Luna | `openai-completions` | 1,050,000 | 128,000 | yes | text, image | | `openai/gpt-5.6-luna-pro` | OpenAI: GPT-5.6 Luna Pro | `openai-completions` | 1,050,000 | 128,000 | yes | text, image | | `openai/gpt-5.6-sol` | OpenAI: GPT-5.6 Sol | `openai-completions` | 1,050,000 | 128,000 | yes | text, image | | `openai/gpt-5.6-sol-pro` | OpenAI: GPT-5.6 Sol Pro | `openai-completions` | 1,050,000 | 128,000 | yes | text, image | | `openai/gpt-5.6-terra` | OpenAI: GPT-5.6 Terra | `openai-completions` | 1,050,000 | 128,000 | yes | text, image | | `openai/gpt-5.6-terra-pro` | OpenAI: GPT-5.6 Terra Pro | `openai-completions` | 1,050,000 | 128,000 | yes | text, image | | `openai/gpt-audio` | OpenAI: GPT Audio | `openai-completions` | 128,000 | 16,384 | no | text | | `openai/gpt-audio-mini` | OpenAI: GPT Audio Mini | `openai-completions` | 128,000 | 16,384 | no | text | | `openai/gpt-chat-latest` | OpenAI: GPT Chat Latest | `openai-completions` | 400,000 | 128,000 | no | text, image | | `openai/gpt-oss-120b` | OpenAI: gpt-oss-120b | `openai-completions` | 131,072 | 131,072 | yes | text | | `openai/gpt-oss-20b` | OpenAI: gpt-oss-20b | `openai-completions` | 131,072 | 131,072 | yes | text | | `openai/gpt-oss-20b:free` | OpenAI: gpt-oss-20b (free) | `openai-completions` | 131,072 | 32,768 | yes | text | | `openai/gpt-oss-safeguard-20b` | OpenAI: gpt-oss-safeguard-20b | `openai-completions` | 131,072 | 65,536 | yes | text | | `openai/o1` | OpenAI: o1 | `openai-completions` | 200,000 | 100,000 | yes | text, image | | `openai/o3` | OpenAI: o3 | `openai-completions` | 200,000 | 100,000 | yes | text, image | | `openai/o3-mini` | OpenAI: o3 Mini | `openai-completions` | 200,000 | 100,000 | yes | text | | `openai/o3-mini-high` | OpenAI: o3 Mini High | `openai-completions` | 200,000 | 100,000 | yes | text | | `openai/o3-pro` | OpenAI: o3 Pro | `openai-completions` | 200,000 | 100,000 | yes | text, image | | `openai/o4-mini` | OpenAI: o4 Mini | `openai-completions` | 200,000 | 100,000 | yes | text, image | | `openai/o4-mini-high` | OpenAI: o4 Mini High | `openai-completions` | 200,000 | 100,000 | yes | text, image | | `openrouter/auto` | Auto Router | `openai-completions` | 2,000,000 | 4,096 | yes | text, image | | `openrouter/auto-beta` | Auto Router (Beta) | `openai-completions` | 2,000,000 | 4,096 | yes | text, image | | `openrouter/free` | Free Models Router | `openai-completions` | 200,000 | 4,096 | yes | text, image | | `poolside/laguna-s-2.1` | Poolside: Laguna S 2.1 | `openai-completions` | 1,048,576 | 131,072 | yes | text | | `poolside/laguna-s-2.1:free` | Poolside: Laguna S 2.1 (free) | `openai-completions` | 262,144 | 32,768 | yes | text | | `poolside/laguna-xs-2.1` | Poolside: Laguna XS 2.1 | `openai-completions` | 262,144 | 32,768 | yes | text | | `poolside/laguna-xs-2.1:free` | Poolside: Laguna XS 2.1 (free) | `openai-completions` | 262,144 | 32,768 | yes | text | | `qwen/qwen-2.5-72b-instruct` | Qwen2.5 72B Instruct | `openai-completions` | 32,768 | 16,384 | no | text | | `qwen/qwen-2.5-7b-instruct` | Qwen: Qwen2.5 7B Instruct | `openai-completions` | 32,768 | 32,768 | no | text | | `qwen/qwen-plus` | Qwen: Qwen-Plus | `openai-completions` | 1,000,000 | 32,768 | no | text | | `qwen/qwen-plus-2025-07-28` | Qwen: Qwen Plus 0728 | `openai-completions` | 1,000,000 | 32,768 | no | text | | `qwen/qwen-plus-2025-07-28:thinking` | Qwen: Qwen Plus 0728 (thinking) | `openai-completions` | 1,000,000 | 32,768 | yes | text | | `qwen/qwen3-14b` | Qwen: Qwen3 14B | `openai-completions` | 131,072 | 8,192 | yes | text | | `qwen/qwen3-235b-a22b` | Qwen: Qwen3 235B A22B | `openai-completions` | 131,072 | 8,192 | yes | text | | `qwen/qwen3-235b-a22b-2507` | Qwen: Qwen3 235B A22B Instruct 2507 | `openai-completions` | 262,144 | 32,768 | no | text | | `qwen/qwen3-235b-a22b-thinking-2507` | Qwen: Qwen3 235B A22B Thinking 2507 | `openai-completions` | 262,144 | 4,096 | yes | text | | `qwen/qwen3-30b-a3b` | Qwen: Qwen3 30B A3B | `openai-completions` | 131,072 | 16,384 | yes | text | | `qwen/qwen3-30b-a3b-instruct-2507` | Qwen: Qwen3 30B A3B Instruct 2507 | `openai-completions` | 262,144 | 32,000 | no | text | | `qwen/qwen3-30b-a3b-thinking-2507` | Qwen: Qwen3 30B A3B Thinking 2507 | `openai-completions` | 81,920 | 32,768 | yes | text | | `qwen/qwen3-32b` | Qwen: Qwen3 32B | `openai-completions` | 131,072 | 16,384 | yes | text | | `qwen/qwen3-8b` | Qwen: Qwen3 8B | `openai-completions` | 131,072 | 8,192 | yes | text | | `qwen/qwen3-coder` | Qwen: Qwen3 Coder 480B A35B | `openai-completions` | 262,144 | 65,536 | no | text | | `qwen/qwen3-coder-30b-a3b-instruct` | Qwen: Qwen3 Coder 30B A3B Instruct | `openai-completions` | 262,144 | 32,768 | no | text | | `qwen/qwen3-coder-flash` | Qwen: Qwen3 Coder Flash | `openai-completions` | 1,000,000 | 65,536 | no | text | | `qwen/qwen3-coder-next` | Qwen: Qwen3 Coder Next | `openai-completions` | 262,144 | 262,144 | no | text | | `qwen/qwen3-coder-plus` | Qwen: Qwen3 Coder Plus | `openai-completions` | 1,000,000 | 65,536 | no | text | | `qwen/qwen3-max` | Qwen: Qwen3 Max | `openai-completions` | 262,144 | 65,536 | no | text | | `qwen/qwen3-max-thinking` | Qwen: Qwen3 Max Thinking | `openai-completions` | 262,144 | 65,536 | yes | text | | `qwen/qwen3-next-80b-a3b-instruct` | Qwen: Qwen3 Next 80B A3B Instruct | `openai-completions` | 262,144 | 16,384 | no | text | | `qwen/qwen3-next-80b-a3b-thinking` | Qwen: Qwen3 Next 80B A3B Thinking | `openai-completions` | 262,144 | 4,096 | yes | text | | `qwen/qwen3-vl-235b-a22b-instruct` | Qwen: Qwen3 VL 235B A22B Instruct | `openai-completions` | 262,144 | 32,768 | no | text, image | | `qwen/qwen3-vl-235b-a22b-thinking` | Qwen: Qwen3 VL 235B A22B Thinking | `openai-completions` | 131,072 | 32,768 | yes | text, image | | `qwen/qwen3-vl-30b-a3b-instruct` | Qwen: Qwen3 VL 30B A3B Instruct | `openai-completions` | 262,144 | 16,384 | no | text, image | | `qwen/qwen3-vl-30b-a3b-thinking` | Qwen: Qwen3 VL 30B A3B Thinking | `openai-completions` | 262,144 | 32,768 | yes | text, image | | `qwen/qwen3-vl-32b-instruct` | Qwen: Qwen3 VL 32B Instruct | `openai-completions` | 131,072 | 32,768 | no | text, image | | `qwen/qwen3-vl-8b-instruct` | Qwen: Qwen3 VL 8B Instruct | `openai-completions` | 262,144 | 32,768 | no | text, image | | `qwen/qwen3-vl-8b-thinking` | Qwen: Qwen3 VL 8B Thinking | `openai-completions` | 131,072 | 32,768 | yes | text, image | | `qwen/qwen3.5-122b-a10b` | Qwen: Qwen3.5-122B-A10B | `openai-completions` | 262,144 | 65,536 | yes | text, image | | `qwen/qwen3.5-27b` | Qwen: Qwen3.5-27B | `openai-completions` | 262,144 | 65,536 | yes | text, image | | `qwen/qwen3.5-35b-a3b` | Qwen: Qwen3.5-35B-A3B | `openai-completions` | 262,144 | 262,144 | yes | text, image | | `qwen/qwen3.5-397b-a17b` | Qwen: Qwen3.5 397B A17B | `openai-completions` | 262,144 | 65,536 | yes | text, image | | `qwen/qwen3.5-9b` | Qwen: Qwen3.5-9B | `openai-completions` | 262,144 | 262,144 | yes | text, image | | `qwen/qwen3.5-flash-02-23` | Qwen: Qwen3.5-Flash | `openai-completions` | 1,000,000 | 65,536 | yes | text, image | | `qwen/qwen3.5-plus-02-15` | Qwen: Qwen3.5 Plus 2026-02-15 | `openai-completions` | 1,000,000 | 65,536 | yes | text, image | | `qwen/qwen3.5-plus-20260420` | Qwen: Qwen3.5 Plus 2026-04-20 | `openai-completions` | 1,000,000 | 65,536 | yes | text, image | | `qwen/qwen3.6-27b` | Qwen: Qwen3.6 27B | `openai-completions` | 262,144 | 131,072 | yes | text, image | | `qwen/qwen3.6-35b-a3b` | Qwen: Qwen3.6 35B A3B | `openai-completions` | 262,144 | 262,144 | yes | text, image | | `qwen/qwen3.6-flash` | Qwen: Qwen3.6 Flash | `openai-completions` | 1,000,000 | 65,536 | yes | text, image | | `qwen/qwen3.6-max-preview` | Qwen: Qwen3.6 Max Preview | `openai-completions` | 262,144 | 65,536 | yes | text | | `qwen/qwen3.6-plus` | Qwen: Qwen3.6 Plus | `openai-completions` | 1,000,000 | 65,536 | yes | text, image | | `qwen/qwen3.7-flash` | Qwen: Qwen3.7 Flash | `openai-completions` | 1,000,000 | 65,536 | yes | text, image | | `qwen/qwen3.7-max` | Qwen: Qwen3.7 Max | `openai-completions` | 1,000,000 | 131,072 | yes | text | | `qwen/qwen3.7-plus` | Qwen: Qwen3.7 Plus | `openai-completions` | 1,000,000 | 131,072 | yes | text, image | | `qwen/qwen3.8-max` | Qwen: Qwen3.8 Max | `openai-completions` | 1,000,000 | 131,072 | yes | text, image | | `rekaai/reka-edge` | Reka Edge | `openai-completions` | 16,384 | 16,384 | no | text, image | | `relace/relace-search` | Relace: Relace Search | `openai-completions` | 256,000 | 128,000 | no | text | | `sakana/fugu-ultra` | Sakana: Fugu Ultra | `openai-completions` | 1,000,000 | 128,000 | yes | text, image | | `sao10k/l3.1-euryale-70b` | Sao10K: Llama 3.1 Euryale 70B v2.2 | `openai-completions` | 131,072 | 16,384 | no | text | | `stepfun/step-3.5-flash` | StepFun: Step 3.5 Flash | `openai-completions` | 262,144 | 65,536 | yes | text | | `stepfun/step-3.7-flash` | StepFun: Step 3.7 Flash | `openai-completions` | 262,144 | 256,000 | yes | text, image | | `tencent/hy3` | Tencent: Hy3 | `openai-completions` | 262,144 | 128,000 | yes | text | | `tencent/hy3-preview` | Tencent: Hy3 preview | `openai-completions` | 262,144 | 4,096 | yes | text | | `thedrummer/unslopnemo-12b` | TheDrummer: UnslopNemo 12B | `openai-completions` | 1,024,000 | 1,024,000 | no | text | | `thinkingmachines/inkling` | Thinking Machines: Inkling | `openai-completions` | 1,048,576 | 4,096 | yes | text, image | | `thinkingmachines/inkling-small` | Thinking Machines: Inkling Small | `openai-completions` | 524,288 | 4,096 | yes | text, image | | `upstage/solar-pro-3` | Upstage: Solar Pro 3 | `openai-completions` | 131,072 | 131,072 | yes | text | | `x-ai/grok-4.20` | SpaceXAI: Grok 4.20 | `openai-completions` | 2,000,000 | 4,096 | yes | text, image | | `x-ai/grok-4.3` | SpaceXAI: Grok 4.3 | `openai-completions` | 1,000,000 | 4,096 | yes | text, image | | `x-ai/grok-4.5` | SpaceXAI: Grok 4.5 | `openai-completions` | 500,000 | 4,096 | yes | text, image | | `x-ai/grok-build-0.1` | SpaceXAI: Grok Build 0.1 | `openai-completions` | 256,000 | 4,096 | yes | text, image | | `xiaomi/mimo-v2.5` | Xiaomi: MiMo-V2.5 | `openai-completions` | 1,050,000 | 131,072 | yes | text, image | | `xiaomi/mimo-v2.5-pro` | Xiaomi: MiMo-V2.5-Pro | `openai-completions` | 1,050,000 | 131,072 | yes | text | | `z-ai/glm-4.5` | Z.ai: GLM 4.5 | `openai-completions` | 131,072 | 98,304 | yes | text | | `z-ai/glm-4.5-air` | Z.ai: GLM 4.5 Air | `openai-completions` | 131,072 | 98,304 | yes | text | | `z-ai/glm-4.5v` | Z.ai: GLM 4.5V | `openai-completions` | 65,536 | 16,384 | yes | text, image | | `z-ai/glm-4.6` | Z.ai: GLM 4.6 | `openai-completions` | 204,800 | 131,072 | yes | text | | `z-ai/glm-4.6v` | Z.ai: GLM 4.6V | `openai-completions` | 131,072 | 32,768 | yes | text, image | | `z-ai/glm-4.7` | Z.ai: GLM 4.7 | `openai-completions` | 204,800 | 131,072 | yes | text | | `z-ai/glm-4.7-flash` | Z.ai: GLM 4.7 Flash | `openai-completions` | 202,752 | 16,384 | yes | text | | `z-ai/glm-5` | Z.ai: GLM 5 | `openai-completions` | 204,800 | 131,072 | yes | text | | `z-ai/glm-5-turbo` | Z.ai: GLM 5 Turbo | `openai-completions` | 202,752 | 131,072 | yes | text | | `z-ai/glm-5.1` | Z.ai: GLM 5.1 | `openai-completions` | 204,800 | 131,072 | yes | text | | `z-ai/glm-5.2` | Z.ai: GLM 5.2 | `openai-completions` | 1,048,576 | 262,144 | yes | text | | `z-ai/glm-5v-turbo` | Z.ai: GLM 5V Turbo | `openai-completions` | 202,752 | 131,072 | yes | text, image | ## prime-inference | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | ------------------------------------------ | --------------------------------- | -------------------- | --------: | ---------: | :-------: | ----------- | | `anthropic/claude-fable-5` | Claude Fable 5 | `openai-completions` | 1,000,000 | 128,000 | yes | text, image | | `anthropic/claude-haiku-4.5` | Claude Haiku 4.5 | `openai-completions` | 200,000 | 64,000 | yes | text, image | | `anthropic/claude-opus-4.1` | Claude Opus 4.1 | `openai-completions` | 200,000 | 32,000 | yes | text, image | | `anthropic/claude-opus-4.5` | Claude Opus 4.5 | `openai-completions` | 200,000 | 64,000 | yes | text, image | | `anthropic/claude-opus-4.6` | Claude Opus 4.6 | `openai-completions` | 1,000,000 | 128,000 | yes | text, image | | `anthropic/claude-opus-4.7` | Claude Opus 4.7 | `openai-completions` | 1,000,000 | 128,000 | yes | text, image | | `anthropic/claude-opus-4.8` | Claude Opus 4.8 | `openai-completions` | 1,000,000 | 128,000 | yes | text, image | | `anthropic/claude-opus-5` | Claude Opus 5 | `openai-completions` | 1,000,000 | 128,000 | yes | text, image | | `anthropic/claude-sonnet-4` | Claude Sonnet 4 | `openai-completions` | 200,000 | 64,000 | yes | text, image | | `anthropic/claude-sonnet-4.5` | Claude Sonnet 4.5 | `openai-completions` | 200,000 | 64,000 | yes | text, image | | `anthropic/claude-sonnet-4.6` | Claude Sonnet 4.6 | `openai-completions` | 1,000,000 | 128,000 | yes | text, image | | `anthropic/claude-sonnet-5` | Claude Sonnet 5 | `openai-completions` | 1,000,000 | 128,000 | yes | text, image | | `deepseek/deepseek-chat` | Deepseek Chat | `openai-completions` | 163,840 | 16,000 | no | text | | `deepseek/deepseek-chat-v3-0324` | Deepseek Chat V3 0324 | `openai-completions` | 163,840 | 65,536 | no | text | | `deepseek/deepseek-chat-v3.1` | Deepseek Chat V3.1 | `openai-completions` | 163,840 | 32,768 | yes | text | | `deepseek/deepseek-v3.1-terminus` | Deepseek V3.1 Terminus | `openai-completions` | 163,840 | 32,768 | yes | text | | `deepseek/deepseek-v3.2` | Deepseek V3.2 | `openai-completions` | 163,840 | 65,536 | yes | text | | `deepseek/deepseek-v3.2-exp` | Deepseek V3.2 EXP | `openai-completions` | 163,840 | 65,536 | yes | text | | `deepseek/deepseek-v4-flash` | Deepseek V4 Flash | `openai-completions` | 1,048,576 | 393,216 | yes | text | | `deepseek/deepseek-v4-flash-0731` | Deepseek V4 Flash 0731 | `openai-completions` | 1,048,576 | 65,536 | yes | text | | `deepseek/deepseek-v4-pro` | Deepseek V4 PRO | `openai-completions` | 1,048,576 | 384,000 | yes | text | | `google/gemini-2.5-flash` | Gemini 2.5 Flash | `openai-completions` | 1,048,576 | 65,535 | yes | text, image | | `google/gemini-2.5-flash-lite` | Gemini 2.5 Flash Lite | `openai-completions` | 1,048,576 | 65,535 | yes | text, image | | `google/gemini-2.5-pro` | Gemini 2.5 PRO | `openai-completions` | 1,048,576 | 65,536 | yes | text, image | | `google/gemini-3-flash-preview` | Gemini 3 Flash Preview | `openai-completions` | 1,048,576 | 65,535 | yes | text, image | | `google/gemini-3.1-pro-preview` | Gemini 3.1 PRO Preview | `openai-completions` | 1,048,576 | 65,536 | yes | text, image | | `google/gemini-3.5-flash` | Gemini 3.5 Flash | `openai-completions` | 1,048,576 | 65,536 | yes | text, image | | `google/gemini-3.6-flash` | Gemini 3.6 Flash | `openai-completions` | 1,048,576 | 65,536 | yes | text, image | | `google/gemma-3-27b-it` | Gemma 3 27B IT | `openai-completions` | 262,144 | 131,072 | no | text, image | | `meta-llama/Llama-3.2-1B-Instruct` | Llama 3.2 1B Instruct | `openai-completions` | 60,000 | 60,000 | no | text | | `meta-llama/Llama-3.2-3B-Instruct` | Llama 3.2 3B Instruct | `openai-completions` | 80,000 | 80,000 | no | text | | `meta-llama/llama-3.3-70b-instruct` | Llama 3.3 70B Instruct | `openai-completions` | 131,072 | 16,384 | no | text | | `meta-llama/llama-4-maverick` | Llama 4 Maverick | `openai-completions` | 1,048,576 | 16,384 | no | text, image | | `minimax/minimax-m2.5` | Minimax M2.5 | `openai-completions` | 204,800 | 196,608 | yes | text | | `minimax/minimax-m2.7` | Minimax M2.7 | `openai-completions` | 204,800 | 131,072 | yes | text | | `minimax/minimax-m3` | Minimax M3 | `openai-completions` | 524,288 | 512,000 | yes | text, image | | `mistralai/mistral-large-2512` | Mistral Large 2512 | `openai-completions` | 262,144 | 8,192 | no | text, image | | `mistralai/mistral-nemo` | Mistral Nemo | `openai-completions` | 131,072 | 16,384 | no | text | | `mistralai/mistral-small-2603` | Mistral Small 2603 | `openai-completions` | 262,144 | 8,192 | yes | text, image | | `mistralai/mixtral-8x22b-instruct` | Mixtral 8X22B Instruct | `openai-completions` | 65,536 | 8,192 | no | text | | `moonshotai/kimi-k2-0905` | Kimi K2 0905 | `openai-completions` | 98,304 | 98,304 | no | text | | `moonshotai/kimi-k2.5` | Kimi K2.5 | `openai-completions` | 262,144 | 65,535 | yes | text, image | | `moonshotai/kimi-k2.6` | Kimi K2.6 | `openai-completions` | 262,144 | 262,144 | yes | text, image | | `moonshotai/kimi-k2.7-code` | Kimi K2.7 Code | `openai-completions` | 262,144 | 262,144 | yes | text, image | | `moonshotai/kimi-k3` | Kimi K3 | `openai-completions` | 1,048,576 | 1,048,576 | yes | text, image | | `nvidia/nemotron-3-nano-30b-a3b` | Nemotron 3 Nano 30B A3B | `openai-completions` | 262,144 | 262,144 | yes | text | | `nvidia/nemotron-3-super-120b-a12b` | Nemotron 3 Super 120B A12B | `openai-completions` | 262,144 | 4,096 | yes | text | | `nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B` | NVIDIA Nemotron 3 Ultra 550B A55B | `openai-completions` | 131,072 | 16,384 | yes | text | | `openai/gpt-4.1` | GPT 4.1 | `openai-completions` | 1,047,576 | 32,768 | no | text, image | | `openai/gpt-4.1-mini` | GPT 4.1 Mini | `openai-completions` | 1,047,576 | 32,768 | no | text, image | | `openai/gpt-4.1-nano` | GPT 4.1 Nano | `openai-completions` | 1,047,576 | 32,768 | no | text, image | | `openai/gpt-4o` | GPT 4O | `openai-completions` | 128,000 | 16,384 | no | text, image | | `openai/gpt-4o-mini` | GPT 4O Mini | `openai-completions` | 128,000 | 16,384 | no | text, image | | `openai/gpt-5` | GPT 5 | `openai-completions` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5-mini` | GPT 5 Mini | `openai-completions` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5-nano` | GPT 5 Nano | `openai-completions` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5.1` | GPT 5.1 | `openai-completions` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5.2` | GPT 5.2 | `openai-completions` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5.2-chat` | GPT 5.2 Chat | `openai-completions` | 128,000 | 16,384 | no | text, image | | `openai/gpt-5.2-pro` | GPT 5.2 PRO | `openai-completions` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5.3-codex` | GPT 5.3 Codex | `openai-completions` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5.4` | GPT 5.4 | `openai-completions` | 1,050,000 | 128,000 | yes | text, image | | `openai/gpt-5.4-mini` | GPT 5.4 Mini | `openai-completions` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5.4-nano` | GPT 5.4 Nano | `openai-completions` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5.4-pro` | GPT 5.4 PRO | `openai-completions` | 1,050,000 | 128,000 | yes | text, image | | `openai/gpt-5.5` | GPT 5.5 | `openai-completions` | 1,050,000 | 128,000 | yes | text, image | | `openai/gpt-5.6` | GPT 5.6 | `openai-completions` | 128,000 | 8,192 | yes | text | | `openai/gpt-5.6-luna` | GPT 5.6 Luna | `openai-completions` | 1,050,000 | 128,000 | yes | text, image | | `openai/gpt-5.6-luna-pro` | GPT 5.6 Luna PRO | `openai-completions` | 1,050,000 | 128,000 | yes | text, image | | `openai/gpt-5.6-sol` | GPT 5.6 SOL | `openai-completions` | 1,050,000 | 128,000 | yes | text, image | | `openai/gpt-5.6-sol-pro` | GPT 5.6 SOL PRO | `openai-completions` | 1,050,000 | 128,000 | yes | text, image | | `openai/gpt-5.6-terra` | GPT 5.6 Terra | `openai-completions` | 1,050,000 | 128,000 | yes | text, image | | `openai/gpt-5.6-terra-pro` | GPT 5.6 Terra PRO | `openai-completions` | 1,050,000 | 128,000 | yes | text, image | | `openai/gpt-oss-120b` | GPT OSS 120B | `openai-completions` | 131,072 | 131,072 | yes | text | | `openai/gpt-oss-20b` | GPT OSS 20B | `openai-completions` | 131,072 | 131,072 | yes | text | | `poolside/laguna-s-2.1` | Laguna S 2.1 | `openai-completions` | 1,048,576 | 131,072 | yes | text | | `poolside/laguna-xs-2.1` | Laguna XS 2.1 | `openai-completions` | 262,144 | 32,768 | yes | text | | `qwen/qwen3-235b-a22b-2507` | QWEN3 235B A22B 2507 | `openai-completions` | 262,144 | 32,768 | no | text | | `qwen/qwen3-30b-a3b-instruct-2507` | QWEN3 30B A3B Instruct 2507 | `openai-completions` | 262,144 | 32,000 | no | text | | `qwen/qwen3-8b` | QWEN3 8B | `openai-completions` | 131,072 | 8,192 | yes | text | | `qwen/qwen3-coder` | QWEN3 Coder | `openai-completions` | 262,144 | 65,536 | no | text | | `qwen/qwen3-coder-next` | QWEN3 Coder Next | `openai-completions` | 262,144 | 262,144 | no | text | | `qwen/qwen3-max` | QWEN3 MAX | `openai-completions` | 262,144 | 65,536 | no | text | | `qwen/qwen3-vl-235b-a22b-instruct` | QWEN3 VL 235B A22B Instruct | `openai-completions` | 262,144 | 32,768 | no | text, image | | `qwen/qwen3-vl-235b-a22b-thinking` | QWEN3 VL 235B A22B Thinking | `openai-completions` | 131,072 | 32,768 | yes | text, image | | `qwen/qwen3-vl-30b-a3b-instruct` | QWEN3 VL 30B A3B Instruct | `openai-completions` | 262,144 | 16,384 | no | text, image | | `qwen/qwen3-vl-8b-instruct` | QWEN3 VL 8B Instruct | `openai-completions` | 262,144 | 32,768 | no | text, image | | `qwen/qwen3.5-35b-a3b` | QWEN3.5 35B A3B | `openai-completions` | 262,144 | 262,144 | yes | text, image | | `qwen/qwen3.5-397b-a17b` | QWEN3.5 397B A17B | `openai-completions` | 262,144 | 65,536 | yes | text, image | | `qwen/qwen3.6-27b` | QWEN3.6 27B | `openai-completions` | 262,144 | 131,072 | yes | text, image | | `qwen/qwen3.6-35b-a3b` | QWEN3.6 35B A3B | `openai-completions` | 262,144 | 262,144 | yes | text, image | | `qwen/qwen3.7-flash` | QWEN3.7 Flash | `openai-completions` | 1,000,000 | 65,536 | yes | text, image | | `x-ai/grok-4.20` | Grok 4.20 | `openai-completions` | 2,000,000 | 30,000 | yes | text, image | | `x-ai/grok-4.20-multi-agent` | Grok 4.20 Multi Agent | `openai-completions` | 2,000,000 | 30,000 | yes | text, image | | `xiaomi/mimo-v2.5` | Mimo V2.5 | `openai-completions` | 1,050,000 | 131,072 | yes | text, image | | `xiaomi/mimo-v2.5-pro` | Mimo V2.5 PRO | `openai-completions` | 1,050,000 | 131,072 | yes | text | | `z-ai/glm-4.5` | GLM 4.5 | `openai-completions` | 131,072 | 98,304 | yes | text | | `z-ai/glm-4.5-air` | GLM 4.5 AIR | `openai-completions` | 131,072 | 98,304 | yes | text | | `z-ai/glm-4.6` | GLM 4.6 | `openai-completions` | 204,800 | 131,072 | yes | text | | `z-ai/glm-4.7` | GLM 4.7 | `openai-completions` | 204,800 | 131,072 | yes | text | | `z-ai/glm-4.7-flash` | GLM 4.7 Flash | `openai-completions` | 202,752 | 16,384 | yes | text | | `z-ai/glm-5` | GLM 5 | `openai-completions` | 204,800 | 131,072 | yes | text | | `z-ai/glm-5.1` | GLM 5.1 | `openai-completions` | 204,800 | 131,072 | yes | text | | `z-ai/glm-5.2` | GLM 5.2 | `openai-completions` | 1,048,576 | 262,144 | yes | text | ## vercel-ai-gateway | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | ------------------------------------- | --------------------------------- | -------------------- | --------: | ---------: | :-------: | ----------- | | `alibaba/qwen-3-14b` | Qwen3-14B | `anthropic-messages` | 40,960 | 16,384 | yes | text | | `alibaba/qwen-3-235b` | Qwen3 235B A22B | `anthropic-messages` | 262,144 | 16,384 | yes | text | | `alibaba/qwen-3-30b` | Qwen3-30B-A3B | `anthropic-messages` | 40,960 | 16,384 | yes | text | | `alibaba/qwen-3-32b` | Qwen 3 32B | `anthropic-messages` | 128,000 | 8,192 | yes | text | | `alibaba/qwen-3.6-max-preview` | Qwen 3.6 Max Preview | `anthropic-messages` | 240,000 | 64,000 | yes | text | | `alibaba/qwen3-235b-a22b-thinking` | Qwen3 VL 235B A22B Thinking | `anthropic-messages` | 131,072 | 32,768 | yes | text, image | | `alibaba/qwen3-coder` | Qwen3 Coder 480B A35B Instruct | `anthropic-messages` | 262,144 | 65,536 | no | text | | `alibaba/qwen3-coder-30b-a3b` | Qwen 3 Coder 30B A3B Instruct | `anthropic-messages` | 262,144 | 8,192 | no | text | | `alibaba/qwen3-coder-next` | Qwen3 Coder Next | `anthropic-messages` | 256,000 | 256,000 | no | text | | `alibaba/qwen3-coder-plus` | Qwen3 Coder Plus | `anthropic-messages` | 1,000,000 | 65,536 | no | text | | `alibaba/qwen3-max` | Qwen3 Max | `anthropic-messages` | 262,144 | 32,768 | no | text | | `alibaba/qwen3-max-preview` | Qwen3 Max Preview | `anthropic-messages` | 262,144 | 32,768 | no | text | | `alibaba/qwen3-max-thinking` | Qwen 3 Max Thinking | `anthropic-messages` | 256,000 | 65,536 | yes | text | | `alibaba/qwen3-next-80b-a3b-instruct` | Qwen3 Next 80B A3B Instruct | `anthropic-messages` | 131,072 | 32,768 | no | text | | `alibaba/qwen3-next-80b-a3b-thinking` | Qwen3 Next 80B A3B Thinking | `anthropic-messages` | 131,072 | 32,768 | yes | text | | `alibaba/qwen3-vl-235b-a22b-instruct` | Qwen3 VL 235B A22B Instruct | `anthropic-messages` | 131,072 | 129,024 | no | text, image | | `alibaba/qwen3-vl-instruct` | Qwen3 VL 235B A22B Instruct | `anthropic-messages` | 131,072 | 129,024 | no | text, image | | `alibaba/qwen3-vl-thinking` | Qwen3 VL 235B A22B Thinking | `anthropic-messages` | 131,072 | 32,768 | yes | text, image | | `alibaba/qwen3.5-flash` | Qwen 3.5 Flash | `anthropic-messages` | 1,000,000 | 64,000 | yes | text, image | | `alibaba/qwen3.5-plus` | Qwen 3.5 Plus | `anthropic-messages` | 1,000,000 | 64,000 | yes | text, image | | `alibaba/qwen3.6-27b` | Qwen 3.6 27B | `anthropic-messages` | 256,000 | 256,000 | yes | text, image | | `alibaba/qwen3.6-plus` | Qwen 3.6 Plus | `anthropic-messages` | 1,000,000 | 64,000 | yes | text, image | | `alibaba/qwen3.7-flash` | Qwen 3.7 Flash | `anthropic-messages` | 991,000 | 64,000 | yes | text, image | | `alibaba/qwen3.7-max` | Qwen 3.7 Max | `anthropic-messages` | 991,000 | 64,000 | yes | text | | `alibaba/qwen3.7-plus` | Qwen 3.7 Plus | `anthropic-messages` | 1,000,000 | 64,000 | yes | text, image | | `alibaba/qwen3.8-max` | Qwen 3.8 Max | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `amazon/nova-2-lite` | Nova 2 Lite | `anthropic-messages` | 1,000,000 | 1,000,000 | yes | text, image | | `amazon/nova-lite` | Nova Lite | `anthropic-messages` | 300,000 | 8,192 | no | text, image | | `amazon/nova-micro` | Nova Micro | `anthropic-messages` | 128,000 | 8,192 | no | text | | `amazon/nova-pro` | Nova Pro | `anthropic-messages` | 300,000 | 8,192 | no | text, image | | `anthropic/claude-3-haiku` | Claude 3 Haiku | `anthropic-messages` | 200,000 | 4,096 | no | text, image | | `anthropic/claude-fable-5` | Claude Fable 5 | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `anthropic/claude-haiku-4.5` | Claude Haiku 4.5 | `anthropic-messages` | 200,000 | 64,000 | yes | text, image | | `anthropic/claude-opus-4` | Claude Opus 4 | `anthropic-messages` | 200,000 | 8,192 | yes | text, image | | `anthropic/claude-opus-4.5` | Claude Opus 4.5 | `anthropic-messages` | 200,000 | 64,000 | yes | text, image | | `anthropic/claude-opus-4.6` | Claude Opus 4.6 | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `anthropic/claude-opus-4.7` | Claude Opus 4.7 | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `anthropic/claude-opus-4.8` | Claude Opus 4.8 | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `anthropic/claude-opus-4.8-fast` | Claude Opus 4.8 (Fast) | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `anthropic/claude-opus-5` | Claude Opus 5 | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `anthropic/claude-opus-5-fast` | Claude Opus 5 (Fast) | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `anthropic/claude-sonnet-4` | Claude Sonnet 4 | `anthropic-messages` | 1,000,000 | 8,192 | yes | text, image | | `anthropic/claude-sonnet-4.5` | Claude Sonnet 4.5 | `anthropic-messages` | 1,000,000 | 64,000 | yes | text, image | | `anthropic/claude-sonnet-4.6` | Claude Sonnet 4.6 | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `anthropic/claude-sonnet-5` | Claude Sonnet 5 | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `arcee-ai/trinity-large-thinking` | Trinity Large Thinking | `anthropic-messages` | 262,100 | 80,000 | yes | text | | `arcee-ai/trinity-mini` | Trinity Mini | `anthropic-messages` | 131,072 | 131,072 | no | text | | `bytedance/seed-1.6` | Seed 1.6 | `anthropic-messages` | 256,000 | 32,000 | yes | text, image | | `bytedance/seed-1.8` | Bytedance Seed 1.8 | `anthropic-messages` | 256,000 | 64,000 | yes | text, image | | `cohere/command-a` | Command A | `anthropic-messages` | 256,000 | 8,000 | no | text | | `deepseek/deepseek-r1` | DeepSeek-R1 | `anthropic-messages` | 128,000 | 8,192 | yes | text | | `deepseek/deepseek-v3` | DeepSeek V3 0324 | `anthropic-messages` | 163,840 | 163,840 | no | text | | `deepseek/deepseek-v3.1` | DeepSeek V3.1 | `anthropic-messages` | 163,840 | 128,000 | yes | text | | `deepseek/deepseek-v3.1-terminus` | DeepSeek V3.1 Terminus | `anthropic-messages` | 131,072 | 65,536 | yes | text | | `deepseek/deepseek-v3.2` | DeepSeek V3.2 | `anthropic-messages` | 128,000 | 8,000 | no | text | | `deepseek/deepseek-v3.2-thinking` | DeepSeek V3.2 Thinking | `anthropic-messages` | 128,000 | 8,000 | yes | text | | `deepseek/deepseek-v4-flash` | DeepSeek V4 Flash | `anthropic-messages` | 1,000,000 | 384,000 | yes | text | | `deepseek/deepseek-v4-flash-0731` | DeepSeek V4 Flash 0731 | `anthropic-messages` | 1,000,000 | 384,000 | yes | text | | `deepseek/deepseek-v4-pro` | DeepSeek V4 Pro | `anthropic-messages` | 1,048,600 | 1,048,600 | yes | text | | `google/gemini-2.5-flash` | Gemini 2.5 Flash | `anthropic-messages` | 1,000,000 | 65,536 | yes | text, image | | `google/gemini-2.5-flash-lite` | Gemini 2.5 Flash Lite | `anthropic-messages` | 1,048,576 | 65,536 | yes | text, image | | `google/gemini-2.5-pro` | Gemini 2.5 Pro | `anthropic-messages` | 1,048,576 | 65,536 | yes | text, image | | `google/gemini-3-flash` | Gemini 3 Flash | `anthropic-messages` | 1,000,000 | 65,000 | yes | text, image | | `google/gemini-3.1-flash-lite` | Gemini 3.1 Flash Lite | `anthropic-messages` | 1,000,000 | 65,000 | yes | text, image | | `google/gemini-3.1-pro-preview` | Gemini 3.1 Pro Preview | `anthropic-messages` | 1,000,000 | 64,000 | yes | text, image | | `google/gemini-3.5-flash` | Gemini 3.5 Flash | `anthropic-messages` | 1,000,000 | 64,000 | yes | text, image | | `google/gemini-3.5-flash-lite` | Gemini 3.5 Flash Lite | `anthropic-messages` | 1,000,000 | 65,000 | yes | text, image | | `google/gemini-3.6-flash` | Gemini 3.6 Flash | `anthropic-messages` | 1,000,000 | 64,000 | yes | text, image | | `google/gemma-4-26b-a4b-it` | Gemma 4 26B A4B IT | `anthropic-messages` | 262,144 | 131,072 | yes | text, image | | `google/gemma-4-31b-it` | Gemma 4 31B IT | `anthropic-messages` | 262,144 | 131,072 | yes | text, image | | `inception/mercury-2` | Mercury 2 | `anthropic-messages` | 128,000 | 128,000 | yes | text | | `inception/mercury-coder-small` | Mercury Coder Small Beta | `anthropic-messages` | 32,000 | 16,384 | no | text | | `inclusionai/ling-3.0-flash-free` | Ling 3.0 Flash | `anthropic-messages` | 256,000 | 256,000 | yes | text | | `interfaze/interfaze-beta` | Interfaze Beta | `anthropic-messages` | 1,000,000 | 32,000 | yes | text, image | | `kwaipilot/kat-coder-air-v2.5` | Kat Coder Air V2.5 | `anthropic-messages` | 256,000 | 80,000 | yes | text, image | | `kwaipilot/kat-coder-pro-v1` | KAT-Coder-Pro V1 | `anthropic-messages` | 256,000 | 32,000 | no | text | | `kwaipilot/kat-coder-pro-v2` | Kat Coder Pro V2 | `anthropic-messages` | 256,000 | 256,000 | yes | text | | `kwaipilot/kat-coder-pro-v2.5` | Kat Coder Pro V2.5 | `anthropic-messages` | 256,000 | 80,000 | yes | text, image | | `meta/llama-3.1-70b` | Llama 3.1 70B Instruct | `anthropic-messages` | 128,000 | 8,192 | no | text | | `meta/llama-3.1-8b` | Llama 3.1 8B Instruct | `anthropic-messages` | 128,000 | 8,192 | no | text | | `meta/llama-3.3-70b` | Llama 3.3 70B Instruct | `anthropic-messages` | 128,000 | 8,192 | no | text | | `meta/llama-4-maverick` | Llama 4 Maverick 17B Instruct | `anthropic-messages` | 128,000 | 8,192 | no | text, image | | `meta/llama-4-scout` | Llama 4 Scout 17B Instruct | `anthropic-messages` | 128,000 | 8,192 | no | text, image | | `meta/muse-spark-1.1` | Muse Spark 1.1 | `anthropic-messages` | 1,048,576 | 1,048,576 | yes | text, image | | `minimax/minimax-m2` | MiniMax M2 | `anthropic-messages` | 205,000 | 205,000 | yes | text | | `minimax/minimax-m2.1` | MiniMax M2.1 | `anthropic-messages` | 204,800 | 131,072 | yes | text | | `minimax/minimax-m2.1-lightning` | MiniMax M2.1 Lightning | `anthropic-messages` | 204,800 | 131,072 | yes | text | | `minimax/minimax-m2.5` | MiniMax M2.5 | `anthropic-messages` | 204,800 | 131,000 | yes | text | | `minimax/minimax-m2.5-highspeed` | MiniMax M2.5 High Speed | `anthropic-messages` | 204,800 | 131,000 | yes | text | | `minimax/minimax-m2.7` | Minimax M2.7 | `anthropic-messages` | 204,800 | 131,000 | yes | text | | `minimax/minimax-m2.7-highspeed` | MiniMax M2.7 High Speed | `anthropic-messages` | 204,800 | 131,100 | yes | text | | `minimax/minimax-m3` | MiniMax M3 | `anthropic-messages` | 1,000,000 | 1,000,000 | yes | text, image | | `mistral/codestral` | Mistral Codestral | `anthropic-messages` | 128,000 | 4,000 | no | text | | `mistral/devstral-2` | Devstral 2 | `anthropic-messages` | 256,000 | 256,000 | no | text | | `mistral/devstral-small-2` | Devstral Small 2 | `anthropic-messages` | 256,000 | 256,000 | no | text, image | | `mistral/magistral-medium` | Magistral Medium 2509 | `anthropic-messages` | 128,000 | 64,000 | yes | text, image | | `mistral/magistral-small` | Magistral Small 2509 | `anthropic-messages` | 128,000 | 64,000 | yes | text, image | | `mistral/ministral-14b` | Ministral 14B | `anthropic-messages` | 256,000 | 256,000 | no | text, image | | `mistral/ministral-3b` | Ministral 3B | `anthropic-messages` | 128,000 | 4,000 | no | text, image | | `mistral/ministral-8b` | Ministral 8B | `anthropic-messages` | 128,000 | 4,000 | no | text, image | | `mistral/mistral-large-3` | Mistral Large 3 | `anthropic-messages` | 256,000 | 256,000 | no | text, image | | `mistral/mistral-medium` | Mistral Medium 3.1 | `anthropic-messages` | 128,000 | 64,000 | no | text, image | | `mistral/mistral-medium-3.5` | Mistral Medium Latest | `anthropic-messages` | 256,000 | 256,000 | yes | text, image | | `mistral/mistral-nemo` | Mistral Nemo 12B | `anthropic-messages` | 128,000 | 128,000 | no | text, image | | `mistral/mistral-small` | Mistral Small | `anthropic-messages` | 32,000 | 4,000 | no | text, image | | `mistral/pixtral-12b` | Pixtral 12B 2409 | `anthropic-messages` | 128,000 | 4,000 | no | text, image | | `moonshotai/kimi-k2` | Kimi K2 Instruct | `anthropic-messages` | 131,072 | 131,072 | no | text | | `moonshotai/kimi-k2-thinking` | Kimi K2 Thinking | `anthropic-messages` | 216,144 | 216,144 | yes | text | | `moonshotai/kimi-k2.5` | Kimi K2.5 | `anthropic-messages` | 262,114 | 262,114 | yes | text, image | | `moonshotai/kimi-k2.6` | Kimi K2.6 | `anthropic-messages` | 262,000 | 262,000 | yes | text, image | | `moonshotai/kimi-k2.7-code` | Kimi K2.7 Code | `anthropic-messages` | 256,000 | 32,768 | yes | text, image | | `moonshotai/kimi-k2.7-code-highspeed` | Kimi K2.7 Code High Speed | `anthropic-messages` | 262,144 | 32,768 | yes | text, image | | `moonshotai/kimi-k3` | Kimi K3 | `anthropic-messages` | 1,000,000 | 131,072 | yes | text, image | | `moonshotai/kimi-k3-fast` | Kimi K3 Fast | `anthropic-messages` | 1,000,000 | 131,072 | yes | text, image | | `nvidia/nemotron-3-nano-30b-a3b` | Nemotron 3 Nano 30B A3B | `anthropic-messages` | 262,144 | 262,144 | yes | text | | `nvidia/nemotron-3-super-120b-a12b` | NVIDIA Nemotron 3 Super 120B A12B | `anthropic-messages` | 256,000 | 32,000 | yes | text | | `nvidia/nemotron-3-ultra-550b-a55b` | Nemotron 3 Ultra | `anthropic-messages` | 1,000,000 | 65,000 | yes | text | | `nvidia/nemotron-nano-12b-v2-vl` | Nvidia Nemotron Nano 12B V2 VL | `anthropic-messages` | 131,072 | 131,072 | yes | text, image | | `nvidia/nemotron-nano-9b-v2` | Nvidia Nemotron Nano 9B V2 | `anthropic-messages` | 131,072 | 131,072 | yes | text | | `openai/gpt-3.5-turbo` | GPT-3.5 Turbo | `anthropic-messages` | 16,385 | 4,096 | no | text | | `openai/gpt-4-turbo` | GPT-4 Turbo | `anthropic-messages` | 128,000 | 4,096 | no | text, image | | `openai/gpt-4.1` | GPT-4.1 | `anthropic-messages` | 1,047,576 | 32,768 | no | text, image | | `openai/gpt-4.1-mini` | GPT-4.1 mini | `anthropic-messages` | 1,047,576 | 32,768 | no | text, image | | `openai/gpt-4.1-nano` | GPT-4.1 nano | `anthropic-messages` | 1,047,576 | 32,768 | no | text, image | | `openai/gpt-4o` | GPT-4o | `anthropic-messages` | 128,000 | 16,384 | no | text, image | | `openai/gpt-4o-mini` | GPT-4o mini | `anthropic-messages` | 128,000 | 16,384 | no | text, image | | `openai/gpt-5` | GPT-5 | `anthropic-messages` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5-codex` | GPT-5-Codex | `anthropic-messages` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5-mini` | GPT-5 mini | `anthropic-messages` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5-nano` | GPT-5 nano | `anthropic-messages` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5-pro` | GPT-5 pro | `anthropic-messages` | 400,000 | 272,000 | yes | text, image | | `openai/gpt-5.1-codex` | GPT-5.1-Codex | `anthropic-messages` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5.1-codex-max` | GPT 5.1 Codex Max | `anthropic-messages` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5.1-codex-mini` | GPT 5.1 Codex Mini | `anthropic-messages` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5.1-instant` | GPT-5.1 Instant | `anthropic-messages` | 128,000 | 16,384 | no | text, image | | `openai/gpt-5.1-thinking` | GPT 5.1 Thinking | `anthropic-messages` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5.2` | GPT 5.2 | `anthropic-messages` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5.2-codex` | GPT 5.2 Codex | `anthropic-messages` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5.2-pro` | GPT 5.2 | `anthropic-messages` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5.3-chat` | GPT-5.3 Chat | `anthropic-messages` | 128,000 | 16,384 | no | text, image | | `openai/gpt-5.3-codex` | GPT 5.3 Codex | `anthropic-messages` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5.4` | GPT 5.4 | `anthropic-messages` | 1,050,000 | 128,000 | yes | text, image | | `openai/gpt-5.4-mini` | GPT 5.4 Mini | `anthropic-messages` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5.4-nano` | GPT 5.4 Nano | `anthropic-messages` | 400,000 | 128,000 | yes | text, image | | `openai/gpt-5.4-pro` | GPT 5.4 Pro | `anthropic-messages` | 1,050,000 | 128,000 | yes | text, image | | `openai/gpt-5.5` | GPT 5.5 | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `openai/gpt-5.5-pro` | GPT 5.5 Pro | `anthropic-messages` | 1,000,000 | 128,000 | yes | text, image | | `openai/gpt-5.6-luna` | GPT 5.6 Luna | `anthropic-messages` | 1,050,000 | 128,000 | yes | text, image | | `openai/gpt-5.6-sol` | GPT 5.6 Sol | `anthropic-messages` | 1,050,000 | 128,000 | yes | text, image | | `openai/gpt-5.6-terra` | GPT 5.6 Terra | `anthropic-messages` | 1,050,000 | 128,000 | yes | text, image | | `openai/gpt-oss-120b` | GPT OSS 120B | `anthropic-messages` | 131,072 | 131,072 | yes | text | | `openai/gpt-oss-20b` | GPT OSS 20B | `anthropic-messages` | 131,072 | 8,192 | yes | text | | `openai/gpt-oss-safeguard-20b` | GPT OSS Safeguard 20B | `anthropic-messages` | 131,072 | 65,536 | yes | text | | `openai/o1` | o1 | `anthropic-messages` | 200,000 | 100,000 | yes | text, image | | `openai/o3` | o3 | `anthropic-messages` | 200,000 | 100,000 | yes | text, image | | `openai/o3-deep-research` | o3-deep-research | `anthropic-messages` | 200,000 | 100,000 | yes | text, image | | `openai/o3-mini` | o3-mini | `anthropic-messages` | 200,000 | 100,000 | yes | text | | `openai/o3-pro` | o3 Pro | `anthropic-messages` | 200,000 | 100,000 | yes | text, image | | `openai/o4-mini` | o4-mini | `anthropic-messages` | 200,000 | 100,000 | yes | text, image | | `poolside/laguna-s-2.1` | Laguna S 2.1 | `anthropic-messages` | 1,000,000 | 131,072 | yes | text | | `poolside/laguna-s-2.1-free` | Laguna S 2.1 Free | `anthropic-messages` | 256,000 | 32,768 | yes | text | | `sakana/fugu-ultra` | Fugu Ultra | `anthropic-messages` | 1,000,000 | 1,000,000 | yes | text, image | | `stepfun/step-3.5-flash` | StepFun 3.5 Flash | `anthropic-messages` | 262,114 | 262,114 | yes | text, image | | `stepfun/step-3.7-flash` | Step 3.7 Flash | `anthropic-messages` | 256,000 | 256,000 | yes | text, image | | `tencent/hy3` | Hy3 | `anthropic-messages` | 262,144 | 262,144 | yes | text | | `thinkingmachines/inkling` | Inkling | `anthropic-messages` | 256,000 | 256,000 | yes | text, image | | `thinkingmachines/inkling-small` | Inkling Small | `anthropic-messages` | 1,000,000 | 1,000,000 | yes | text, image | | `xai/grok-4.1-fast-non-reasoning` | Grok 4.1 Fast Non-Reasoning | `anthropic-messages` | 1,000,000 | 1,000,000 | no | text, image | | `xai/grok-4.1-fast-reasoning` | Grok 4.1 Fast Reasoning | `anthropic-messages` | 1,000,000 | 1,000,000 | yes | text, image | | `xai/grok-4.20-multi-agent` | Grok 4.20 Multi-Agent | `anthropic-messages` | 2,000,000 | 2,000,000 | yes | text, image | | `xai/grok-4.20-multi-agent-beta` | Grok 4.20 Multi Agent Beta | `anthropic-messages` | 2,000,000 | 2,000,000 | yes | text, image | | `xai/grok-4.20-non-reasoning` | Grok 4.20 Non-Reasoning | `anthropic-messages` | 2,000,000 | 2,000,000 | no | text, image | | `xai/grok-4.20-non-reasoning-beta` | Grok 4.20 Beta Non-Reasoning | `anthropic-messages` | 2,000,000 | 2,000,000 | no | text, image | | `xai/grok-4.20-reasoning` | Grok 4.20 Reasoning | `anthropic-messages` | 2,000,000 | 2,000,000 | yes | text, image | | `xai/grok-4.20-reasoning-beta` | Grok 4.20 Beta Reasoning | `anthropic-messages` | 2,000,000 | 2,000,000 | yes | text, image | | `xai/grok-4.3` | Grok 4.3 | `anthropic-messages` | 1,000,000 | 1,000,000 | yes | text, image | | `xai/grok-4.5` | Grok 4.5 | `anthropic-messages` | 500,000 | 500,000 | yes | text, image | | `xai/grok-build-0.1` | Grok Build 0.1 | `anthropic-messages` | 256,000 | 256,000 | yes | text, image | | `xiaomi/mimo-v2.5` | MiMo M2.5 | `anthropic-messages` | 1,050,000 | 131,100 | yes | text, image | | `xiaomi/mimo-v2.5-pro` | MiMo V2.5 Pro | `anthropic-messages` | 1,050,000 | 131,000 | yes | text | | `zai/glm-4.5` | GLM 4.5 | `anthropic-messages` | 128,000 | 96,000 | yes | text | | `zai/glm-4.5-air` | GLM 4.5 Air | `anthropic-messages` | 128,000 | 96,000 | yes | text | | `zai/glm-4.5v` | GLM 4.5V | `anthropic-messages` | 66,000 | 16,000 | yes | text, image | | `zai/glm-4.6` | GLM 4.6 | `anthropic-messages` | 200,000 | 96,000 | yes | text | | `zai/glm-4.6v` | GLM-4.6V | `anthropic-messages` | 128,000 | 24,000 | yes | text, image | | `zai/glm-4.6v-flash` | GLM-4.6V-Flash | `anthropic-messages` | 128,000 | 24,000 | yes | text, image | | `zai/glm-4.7` | GLM 4.7 | `anthropic-messages` | 200,000 | 120,000 | yes | text | | `zai/glm-4.7-flash` | GLM 4.7 Flash | `anthropic-messages` | 200,000 | 131,000 | yes | text | | `zai/glm-4.7-flashx` | GLM 4.7 FlashX | `anthropic-messages` | 200,000 | 128,000 | yes | text | | `zai/glm-5` | GLM 5 | `anthropic-messages` | 202,800 | 131,100 | yes | text | | `zai/glm-5-turbo` | GLM 5 Turbo | `anthropic-messages` | 202,800 | 131,100 | yes | text | | `zai/glm-5.1` | GLM 5.1 | `anthropic-messages` | 202,000 | 202,000 | yes | text | | `zai/glm-5.2` | GLM 5.2 | `anthropic-messages` | 1,000,000 | 128,000 | yes | text | | `zai/glm-5.2-fast` | GLM 5.2 Fast | `anthropic-messages` | 1,000,000 | 128,000 | yes | text | | `zai/glm-5v-turbo` | GLM 5V Turbo | `anthropic-messages` | 200,000 | 128,000 | yes | text, image | ## xai | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | ------------------------------ | ------------------------- | -------------------- | --------: | ---------: | :-------: | ----------- | | `grok-4.20-0309-non-reasoning` | Grok 4.20 (Non-Reasoning) | `openai-completions` | 1,000,000 | 30,000 | no | text, image | | `grok-4.20-0309-reasoning` | Grok 4.20 (Reasoning) | `openai-completions` | 1,000,000 | 30,000 | yes | text, image | | `grok-4.3` | Grok 4.3 | `openai-completions` | 1,000,000 | 30,000 | yes | text, image | | `grok-4.5` | Grok 4.5 | `openai-completions` | 500,000 | 500,000 | yes | text, image | | `grok-build-0.1` | Grok Build 0.1 | `openai-completions` | 256,000 | 256,000 | yes | text, image | | `grok-code-fast-1` | Grok Code Fast 1 | `openai-completions` | 32,768 | 8,192 | no | text | ## xiaomi | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | -------------------------- | ------------------------ | -------------------- | --------: | ---------: | :-------: | ----------- | | `mimo-v2-flash` | MiMo-V2-Flash | `anthropic-messages` | 262,144 | 65,536 | yes | text | | `mimo-v2-omni` | MiMo-V2-Omni | `anthropic-messages` | 262,144 | 131,072 | yes | text, image | | `mimo-v2-pro` | MiMo-V2-Pro | `anthropic-messages` | 1,048,576 | 131,072 | yes | text | | `mimo-v2.5` | MiMo-V2.5 | `anthropic-messages` | 1,048,576 | 131,072 | yes | text, image | | `mimo-v2.5-pro` | MiMo-V2.5-Pro | `anthropic-messages` | 1,048,576 | 131,072 | yes | text | | `mimo-v2.5-pro-ultraspeed` | MiMo-V2.5-Pro-UltraSpeed | `anthropic-messages` | 1,048,576 | 131,072 | yes | text | ## xiaomi-token-plan-ams | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | -------------------------- | ------------------------ | -------------------- | --------: | ---------: | :-------: | ----------- | | `mimo-v2-flash` | MiMo-V2-Flash | `anthropic-messages` | 262,144 | 65,536 | yes | text | | `mimo-v2-omni` | MiMo-V2-Omni | `anthropic-messages` | 262,144 | 131,072 | yes | text, image | | `mimo-v2-pro` | MiMo-V2-Pro | `anthropic-messages` | 1,048,576 | 131,072 | yes | text | | `mimo-v2.5` | MiMo-V2.5 | `anthropic-messages` | 1,048,576 | 131,072 | yes | text, image | | `mimo-v2.5-pro` | MiMo-V2.5-Pro | `anthropic-messages` | 1,048,576 | 131,072 | yes | text | | `mimo-v2.5-pro-ultraspeed` | MiMo-V2.5-Pro-UltraSpeed | `anthropic-messages` | 1,048,576 | 131,072 | yes | text | ## xiaomi-token-plan-cn | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | -------------------------- | ------------------------ | -------------------- | --------: | ---------: | :-------: | ----------- | | `mimo-v2-flash` | MiMo-V2-Flash | `anthropic-messages` | 262,144 | 65,536 | yes | text | | `mimo-v2-omni` | MiMo-V2-Omni | `anthropic-messages` | 262,144 | 131,072 | yes | text, image | | `mimo-v2-pro` | MiMo-V2-Pro | `anthropic-messages` | 1,048,576 | 131,072 | yes | text | | `mimo-v2.5` | MiMo-V2.5 | `anthropic-messages` | 1,048,576 | 131,072 | yes | text, image | | `mimo-v2.5-pro` | MiMo-V2.5-Pro | `anthropic-messages` | 1,048,576 | 131,072 | yes | text | | `mimo-v2.5-pro-ultraspeed` | MiMo-V2.5-Pro-UltraSpeed | `anthropic-messages` | 1,048,576 | 131,072 | yes | text | ## xiaomi-token-plan-sgp | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | -------------------------- | ------------------------ | -------------------- | --------: | ---------: | :-------: | ----------- | | `mimo-v2-flash` | MiMo-V2-Flash | `anthropic-messages` | 262,144 | 65,536 | yes | text | | `mimo-v2-omni` | MiMo-V2-Omni | `anthropic-messages` | 262,144 | 131,072 | yes | text, image | | `mimo-v2-pro` | MiMo-V2-Pro | `anthropic-messages` | 1,048,576 | 131,072 | yes | text | | `mimo-v2.5` | MiMo-V2.5 | `anthropic-messages` | 1,048,576 | 131,072 | yes | text, image | | `mimo-v2.5-pro` | MiMo-V2.5-Pro | `anthropic-messages` | 1,048,576 | 131,072 | yes | text | | `mimo-v2.5-pro-ultraspeed` | MiMo-V2.5-Pro-UltraSpeed | `anthropic-messages` | 1,048,576 | 131,072 | yes | text | ## zai | Model ID | Display name | API | Context | Max output | Reasoning | Inputs | | ------------------- | ----------------- | -------------------- | --------: | ---------: | :-------: | ------ | | `glm-4.7` | GLM-4.7 | `openai-completions` | 204,800 | 131,072 | yes | text | | `glm-5-turbo` | GLM-5-Turbo | `openai-completions` | 200,000 | 131,072 | yes | text | | `glm-5.2` | GLM-5.2 | `openai-completions` | 1,000,000 | 131,072 | yes | text | | `glm-5.2-highspeed` | GLM-5.2 Highspeed | `openai-completions` | 1,000,000 | 131,072 | yes | text |