← directory / providers / openrouter
OpenRouter
aggregator169
models served
OPENROUTER_API_KEY
auth
openrouter.ai/api/v1
base url
OpenAI-compatible chat completions surface; routes to many upstream providers. docs →
01Request template
Every model below is invoked with this shape — swap in the provider model ID from the table.
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "content-type: application/json" \
-d '{
"model": "{{MODEL_ID}}",
"messages": [{"role": "user", "content": "Hello, world"}]
}'02Models served · newest first
| Model | Provider model ID | In $/M | Out $/M | Context |
|---|---|---|---|---|
| Gemini Flash LatestGoogle | google/gemini-flash-latest | 0.50 | 3.00 | 1M |
| Gemini 3.1 Flash LiteGoogle | google/gemini-3.1-flash-lite | 0.25 | 1.50 | 1M |
| Qwen3.6 FlashAlibaba Qwen | qwen/qwen3.6-flash | 0.19 | 1.13 | 1M |
| DeepSeek V4 FlashDeepSeek | deepseek/deepseek-v4-flash | 0.13 | 0.25 | 1M |
| DeepSeek V4 ProDeepSeek | deepseek/deepseek-v4-pro | 0.43 | 0.87 | 1M |
| GPT-5.5OpenAI | openai/gpt-5.5 | 5.00 | 30.00 | 1.1M |
| GPT-5.5 ProOpenAI | openai/gpt-5.5-pro | 30.00 | 180.00 | 1.1M |
| MiMo-V2.5Xiaomi | xiaomi/mimo-v2.5 | 0.40 | 2.00 | 1M |
| MiMo-V2.5-ProXiaomi | xiaomi/mimo-v2.5-pro | 1.00 | 3.00 | 1M |
| Qwen3.6 27BAlibaba Qwen | qwen/qwen3.6-27b | 0.32 | 3.20 | 262K |
| Kimi K2.6Moonshot AI | moonshotai/kimi-k2.6 | 0.73 | 3.49 | 262K |
| Hy3 previewTencent | tencent/hy3-preview | 0.07 | 0.26 | 262K |
| Qwen3.6 Max PreviewAlibaba Qwen | qwen/qwen3.6-max-preview | 1.04 | 6.24 | 262K |
| Grok 4.3xAI | x-ai/grok-4.3 | 1.25 | 2.50 | 1M |
| Qwen3.6 35B-A3BAlibaba Qwen | qwen/qwen3.6-35b-a3b | 0.15 | 1.00 | 262K |
| Claude Opus 4.7Anthropic | anthropic/claude-opus-4.7 | 5.00 | 25.00 | 1M |
| GLM-5.1Zhipuai | z-ai/glm-5.1 | 0.98 | 3.08 | 203K |
| Gemma 4 26B A4B ITGoogle | google/gemma-4-26b-a4b-it | 0.06 | 0.33 | 262K |
| Gemma 4 31B ITGoogle | google/gemma-4-31b-it | 0.12 | 0.37 | 262K |
| Qwen3.6 PlusAlibaba Qwen | qwen/qwen3.6-plus | 0.33 | 1.95 | 1M |
| GLM-5V-TurboZhipuai | z-ai/glm-5v-turbo | 1.20 | 4.00 | 203K |
| Trinity Large ThinkingArcee Ai | arcee-ai/trinity-large-thinking:free | — | — | 262K |
| Lyria 3 Clip PreviewGoogle | google/lyria-3-clip-preview | — | — | 1M |
| Lyria 3 Pro PreviewGoogle | google/lyria-3-pro-preview | — | — | 1M |
| MiMo-V2-OmniXiaomi | xiaomi/mimo-v2-omni | 0.40 | 2.00 | 262K |
| MiMo-V2-ProXiaomi | xiaomi/mimo-v2-pro | 1.00 | 3.00 | 1M |
| MiniMax-M2.7MiniMax | minimax/minimax-m2.7 | 0.28 | 1.20 | 197K |
| GPT-5.4 miniOpenAI | openai/gpt-5.4-mini | 0.75 | 4.50 | 400K |
| GPT-5.4 nanoOpenAI | openai/gpt-5.4-nano | 0.20 | 1.25 | 400K |
| GLM-5-TurboZhipuai | z-ai/glm-5-turbo | 1.20 | 4.00 | 203K |
| Mistral Small 4Mistral AI | mistralai/mistral-small-2603 | 0.15 | 0.60 | 262K |
| Nemotron 3 Super 120B A12BNVIDIA | nvidia/nemotron-3-super-120b-a12b | 0.09 | 0.45 | 262K |
| GPT-5.4OpenAI | openai/gpt-5.4 | 2.50 | 15.00 | 1.1M |
| GPT-5.4 ProOpenAI | openai/gpt-5.4-pro | 30.00 | 180.00 | 1.1M |
| Gemini 3.1 Flash Lite PreviewGoogle | google/gemini-3.1-flash-lite-preview | 0.25 | 1.50 | 1M |
| Nano Banana 2Google | google/gemini-3.1-flash-image-preview | 0.50 | 3.00 | 66K |
| Qwen3.5 122B-A10BAlibaba Qwen | qwen/qwen3.5-122b-a10b | 0.26 | 2.08 | 262K |
| Qwen3.5 27BAlibaba Qwen | qwen/qwen3.5-27b | 0.20 | 1.56 | 262K |
| Qwen3.5 35B-A3BAlibaba Qwen | qwen/qwen3.5-35b-a3b | 0.14 | 1.00 | 262K |
| Qwen3.5 9BAlibaba Qwen | qwen/qwen3.5-9b | 0.04 | 0.15 | 262K |
| Gemini 3.1 Pro PreviewGoogle | google/gemini-3.1-pro-preview | 2.00 | 12.00 | 1M |
| Gemini 3.1 Pro Preview Custom ToolsGoogle | google/gemini-3.1-pro-preview-customtools | 2.00 | 12.00 | 1M |
| Claude Sonnet 4.6Anthropic | anthropic/claude-sonnet-4.6 | 3.00 | 15.00 | 1M |
| Qwen3.5 397B-A17BAlibaba Qwen | qwen/qwen3.5-397b-a17b | 0.39 | 2.34 | 262K |
| Seed 2.0 LiteByteDance Seed | bytedance-seed/seed-2.0-lite | 0.25 | 2.00 | 262K |
| Seed 2.0 MiniByteDance Seed | bytedance-seed/seed-2.0-mini | 0.10 | 0.40 | 262K |
| GLM-5Zhipuai | z-ai/glm-5 | 0.60 | 1.92 | 203K |
| MiniMax-M2.5MiniMax | minimax/minimax-m2.5 | 0.15 | 1.15 | 197K |
| Claude Opus 4.6Anthropic | anthropic/claude-opus-4.6 | 5.00 | 25.00 | 1M |
| GPT-5.3 CodexOpenAI | openai/gpt-5.3-codex | 1.75 | 14.00 | 400K |
| Qwen3 Coder NextAlibaba Qwen | qwen/qwen3-coder-next | 0.11 | 0.80 | 262K |
| Step 3.5 FlashStepfun | stepfun/step-3.5-flash | 0.10 | 0.30 | 262K |
| Trinity Large PreviewArcee Ai | arcee-ai/trinity-large-preview | 0.15 | 0.45 | 131K |
| MiniMax-M2 HerMiniMax | minimax/minimax-m2-her | 0.30 | 1.20 | 66K |
| GLM-4.7-FlashZhipuai | z-ai/glm-4.7-flash | 0.06 | 0.40 | 203K |
| Kimi K2.5Moonshot AI | moonshotai/kimi-k2.5 | 0.40 | 1.90 | 262K |
| MiniMax-M2.1MiniMax | minimax/minimax-m2.1 | 0.29 | 0.95 | 197K |
| GLM-4.7Zhipuai | z-ai/glm-4.7 | 0.40 | 1.75 | 203K |
| Gemini 3 Flash PreviewGoogle | google/gemini-3-flash-preview | 0.50 | 3.00 | 1M |
| MiMo-V2-FlashXiaomi | xiaomi/mimo-v2-flash | 0.10 | 0.30 | 262K |
| Nemotron 3 Nano 30B A3BNVIDIA | nvidia/nemotron-3-nano-30b-a3b:free | — | — | 256K |
| GPT-5.2OpenAI | openai/gpt-5.2 | 1.75 | 14.00 | 400K |
| GPT-5.2 CodexOpenAI | openai/gpt-5.2-codex | 1.75 | 14.00 | 400K |
| GPT-5.2 ProOpenAI | openai/gpt-5.2-pro | 21.00 | 168.00 | 400K |
| Devstral 2Mistral AI | mistralai/devstral-2512 | 0.40 | 2.00 | 262K |
| GLM-4.6VZhipuai | z-ai/glm-4.6v | 0.30 | 0.90 | 131K |
| DeepSeek ChatDeepSeek | deepseek/deepseek-chat | 0.32 | 0.89 | 164K |
| Trinity MiniArcee Ai | arcee-ai/trinity-mini | 0.04 | 0.15 | 131K |
| Claude Opus 4.5Anthropic | anthropic/claude-opus-4.5 | 5.00 | 25.00 | 200K |
| Nano Banana ProGoogle | google/gemini-3-pro-image-preview | 2.00 | 12.00 | 66K |
| Grok 4.1 FastxAI | x-ai/grok-4.1-fast | 0.20 | 0.50 | 2M |
| Gemini 3 ProGoogle | google/gemini-3-pro-preview | 2.00 | 12.00 | 1M |
| GPT-5.1OpenAI | openai/gpt-5.1 | 1.25 | 10.00 | 400K |
| GPT-5.1 CodexOpenAI | openai/gpt-5.1-codex | 1.25 | 10.00 | 400K |
| GPT-5.1 Codex MaxOpenAI | openai/gpt-5.1-codex-max | 1.25 | 10.00 | 400K |
| GPT-5.1 Codex miniOpenAI | openai/gpt-5.1-codex-mini | 0.25 | 2.00 | 400K |
| Kimi K2 ThinkingMoonshot AI | moonshotai/kimi-k2-thinking | 0.60 | 2.50 | 262K |
| Nemotron Nano 12B v2 VLNVIDIA | nvidia/nemotron-nano-12b-v2-vl:free | — | — | 128K |
| MiniMax-M2MiniMax | minimax/minimax-m2 | 0.26 | 1.00 | 197K |
| Claude Haiku 4.5Anthropic | anthropic/claude-haiku-4.5 | 1.00 | 5.00 | 200K |
| Seed 1.6ByteDance Seed | bytedance-seed/seed-1.6 | 0.25 | 2.00 | 262K |
| GPT-5 ProOpenAI | openai/gpt-5-pro | 15.00 | 120.00 | 400K |
| GLM-4.6Zhipu AI (Z.ai) | z-ai/glm-4.6 | 0.60 | 2.20 | 200K |
| Claude Sonnet 4.5Anthropic | anthropic/claude-sonnet-4.5 | 3.00 | 15.00 | 200K |
| DeepSeek V3.2DeepSeek | deepseek/deepseek-v3.2-exp | 0.28 | 0.42 | 128K |
| Qwen3 MaxAlibaba Qwen | qwen/qwen3-max | 0.78 | 3.90 | 262K |
| Qwen3 VL 235B A22B InstructAlibaba Qwen | qwen/qwen3-vl-235b-a22b-instruct | 0.20 | 0.88 | 262K |
| Qwen3 VL 235B A22B ThinkingAlibaba Qwen | qwen/qwen3-vl-235b-a22b-thinking | 0.26 | 2.60 | 131K |
| Grok 4 FastxAI | x-ai/grok-4-fast | 0.20 | 0.50 | 2M |
| GPT-5-CodexOpenAI | openai/gpt-5-codex | 1.25 | 10.00 | 400K |
| Kimi K2 (0905)Moonshot AI | moonshotai/kimi-k2-0905 | 0.60 | 2.50 | 262K |
| Qwen3-Next 80B-A3B (Thinking)Alibaba Qwen | qwen/qwen3-next-80b-a3b-thinking | 0.10 | 0.78 | 131K |
| Qwen3-Next 80B-A3B InstructAlibaba Qwen | qwen/qwen3-next-80b-a3b-instruct | 0.09 | 1.10 | 262K |
| Seed 1.6 FlashByteDance Seed | bytedance-seed/seed-1.6-flash | 0.07 | 0.30 | 262K |
| Grok Code Fast 1xAI | x-ai/grok-code-fast-1 | 0.20 | 1.50 | 256K |
| Nano BananaGoogle | google/gemini-2.5-flash-image | 0.30 | 2.50 | 33K |
| Nemotron Nano 9B v2NVIDIA | nvidia/nemotron-nano-9b-v2:free | — | — | 128K |
| GLM-4.5VZhipuai | z-ai/glm-4.5v | 0.60 | 1.80 | 66K |
| GPT-5OpenAI | openai/gpt-5 | 1.25 | 10.00 | 400K |
| GPT-5 miniOpenAI | openai/gpt-5-mini | 0.25 | 2.00 | 400K |
| GPT-5 nanoOpenAI | openai/gpt-5-nano | 0.05 | 0.40 | 400K |
| Claude Opus 4.1Anthropic | anthropic/claude-opus-4.1 | 15.00 | 75.00 | 200K |
| GPT OSS 20BOpenAI | openai/gpt-oss-20b:free | — | — | 131K |
| gpt-oss-120bOpenAI | openai/gpt-oss-120b | — | — | 131K |
| GLM-4.5Zhipuai | z-ai/glm-4.5 | 0.60 | 2.20 | 131K |
| GLM-4.5-AirZhipuai | z-ai/glm-4.5-air:free | — | — | 131K |
| Qwen3 Coder FlashAlibaba Qwen | qwen/qwen3-coder-flash | 0.20 | 0.97 | 1M |
| Llama 3.3 Nemotron Super 49B v1.5NVIDIA | nvidia/llama-3.3-nemotron-super-49b-v1.5 | 0.10 | 0.40 | 131K |
| Qwen3 Coder PlusAlibaba Qwen | qwen/qwen3-coder-plus | 0.65 | 3.25 | 1M |
| Qwen3 Coder 480BAlibaba Qwen | qwen/qwen3-coder | — | — | 262K |
| Devstral MediumMistral AI | mistralai/devstral-medium | 0.40 | 2.00 | 131K |
| Devstral SmallMistral AI | mistralai/devstral-small | 0.10 | 0.30 | 131K |
| Grok 4xAI | x-ai/grok-4 | 3.00 | 15.00 | 256K |
| Gemini 2.5 Flash-LiteGoogle | google/gemini-2.5-flash-lite | 0.10 | 0.40 | 1M |
| Magistral MediumMistral AI | mistralai/magistral-medium | 2.00 | 5.00 | 128K |
| o3-proOpenAI | openai/o3-pro | 20.00 | 80.00 | 200K |
| Claude Sonnet 4Anthropic | anthropic/claude-sonnet-4 | 3.00 | 15.00 | 200K |
| Mistral Medium 3Mistral AI | mistralai/mistral-medium-3 | 0.40 | 2.00 | 131K |
| Qwen3 235B-A22BAlibaba Qwen | qwen/qwen3-235b-a22b-2507 | — | — | 262K |
| Qwen3 30B A3BAlibaba Qwen | qwen/qwen3-30b-a3b | 0.09 | 0.45 | 41K |
| Gemini 2.5 FlashGoogle | google/gemini-2.5-flash | 0.30 | 2.50 | 1M |
| OpenAI o3OpenAI | openai/o3 | 2.00 | 8.00 | 200K |
| OpenAI o4-miniOpenAI | openai/o4-mini | 1.10 | 4.40 | 200K |
| GPT-4.1OpenAI | openai/gpt-4.1 | 2.00 | 8.00 | 1M |
| GPT-4.1 miniOpenAI | openai/gpt-4.1-mini | 0.40 | 1.60 | 1M |
| GPT-4.1 nanoOpenAI | openai/gpt-4.1-nano | 0.10 | 0.40 | 1M |
| Llama 4 MaverickMeta | meta-llama/llama-4-maverick | — | — | 1M |
| Llama 4 ScoutMeta | meta-llama/llama-4-scout | — | — | 10M |
| Qwen3 32BAlibaba Qwen | qwen/qwen3-32b | 0.08 | 0.28 | 41K |
| Qwen3-Coder 30B-A3B InstructAlibaba Qwen | qwen/qwen3-coder-30b-a3b-instruct | 0.07 | 0.27 | 160K |
| Gemini 2.5 ProGoogle | google/gemini-2.5-pro | 1.25 | 10.00 | 1M |
| o1-proOpenAI | openai/o1-pro | 150.00 | 600.00 | 200K |
| Mistral Small 3.1 24BMistral AI | mistralai/mistral-small-3.1-24b-instruct | 0.35 | 0.56 | 128K |
| Command ACohere | cohere/command-a | 2.50 | 10.00 | 256K |
| Command ACohere | cohere/command-a | 2.50 | 10.00 | 256K |
| Claude 3.7 SonnetAnthropic | anthropic/claude-3.7-sonnet | 3.00 | 15.00 | 200K |
| Sonar Deep ResearchPerplexity | perplexity/sonar-deep-research | 2.00 | 8.00 | 128K |
| DeepSeek-R1DeepSeek | deepseek/deepseek-r1 | 0.70 | 2.50 | 64K |
| DeepSeek-R1-Distill-Qwen-32BDeepSeek | deepseek/deepseek-r1-distill-qwen-32b | 0.29 | 0.29 | 33K |
| CodestralMistral AI | mistralai/codestral-2501 | 0.30 | 0.90 | 256K |
| o3-miniOpenAI | openai/o3-mini | 1.10 | 4.40 | 200K |
| Llama 3.3 70BMeta | meta-llama/llama-3.3-70b-instruct | — | — | 131K |
| Llama-3.3-70B-InstructMeta | meta-llama/llama-3.3-70b-instruct:free | — | — | 66K |
| o1OpenAI | openai/o1 | 15.00 | 60.00 | 200K |
| Command R7BCohere | cohere/command-r7b-12-2024 | 0.04 | 0.15 | 128K |
| GPT-4o (2024-11-20)OpenAI | openai/gpt-4o-2024-11-20 | 2.50 | 10.00 | 128K |
| Mistral Large 2.1Mistral AI | mistralai/mistral-large-2411 | 2.00 | 6.00 | 131K |
| Claude 3.5 HaikuAnthropic | anthropic/claude-3.5-haiku | 0.80 | 4.00 | 200K |
| Mistral Large 3Mistral AI | mistralai/mistral-large-2512 | 0.50 | 1.50 | 262K |
| Llama-3.2-11B-Vision-InstructMeta | meta-llama/llama-3.2-11b-vision-instruct | 0.24 | 0.24 | 131K |
| Qwen2.5-VL 72B InstructAlibaba Qwen | qwen/qwen2.5-vl-72b-instruct | 0.25 | 0.75 | 32K |
| Command RCohere | cohere/command-r-08-2024 | 0.15 | 0.60 | 128K |
| Command R+Cohere | cohere/command-r-plus-08-2024 | 2.50 | 10.00 | 128K |
| GPT-4o (2024-08-06)OpenAI | openai/gpt-4o-2024-08-06 | 2.50 | 10.00 | 128K |
| Llama-3.1-8B-InstructMeta | meta-llama/llama-3.1-8b-instruct | 0.02 | 0.05 | 16K |
| Llama-Guard-3-8BMeta | meta-llama/llama-guard-3-8b | 0.48 | 0.03 | 131K |
| GPT-4o miniOpenAI | openai/gpt-4o-mini | 0.15 | 0.60 | 128K |
| Mistral NemoMistral AI | mistralai/mistral-nemo | 0.02 | 0.03 | 131K |
| o3-deep-researchOpenAI | openai/o3-deep-research | 10.00 | 40.00 | 200K |
| o4-mini-deep-researchOpenAI | openai/o4-mini-deep-research | 2.00 | 8.00 | 200K |
| GPT-4oOpenAI | openai/gpt-4o | 2.50 | 10.00 | 128K |
| GPT-4o (2024-05-13)OpenAI | openai/gpt-4o-2024-05-13 | 5.00 | 15.00 | 128K |
| Qwen PlusAlibaba Qwen | qwen/qwen-plus | 0.26 | 0.78 | 1M |
| SonarPerplexity | perplexity/sonar | 1.00 | 1.00 | 127K |
| Sonar ProPerplexity | perplexity/sonar-pro | 3.00 | 15.00 | 200K |
| Sonar Reasoning ProPerplexity | perplexity/sonar-reasoning-pro | 2.00 | 8.00 | 128K |
| GPT-4OpenAI | openai/gpt-4 | 30.00 | 60.00 | 8K |
| GPT-4 TurboOpenAI | openai/gpt-4-turbo | 10.00 | 30.00 | 128K |
| GPT-3.5-turboOpenAI | openai/gpt-3.5-turbo | 0.50 | 1.50 | 16K |
Dimmed prices are canonical — this provider's own quote isn't captured yet.