Skip to main content

OpenRouter

Status: ✅ Supported

OpenRouter provides unified access to multiple AI models through a single API.

Supported Models​

Anthropic​

Model IDNameContext
anthropic/claude-3.5-haikuClaude Haiku 3.5200K
anthropic/claude-haiku-4.5Claude Haiku 4.5200K
anthropic/claude-opus-4Claude Opus 4200K
anthropic/claude-opus-4.1Claude Opus 4.1200K
anthropic/claude-opus-4.5Claude Opus 4.5200K
anthropic/claude-opus-4.6Claude Opus 4.61M
anthropic/claude-opus-4.7Claude Opus 4.71M
anthropic/claude-3.7-sonnetClaude Sonnet 3.7200K
anthropic/claude-sonnet-4Claude Sonnet 4200K
anthropic/claude-sonnet-4.5Claude Sonnet 4.51M
anthropic/claude-sonnet-4.6Claude Sonnet 4.61M

Arcee Ai​

Model IDNameContext
arcee-ai/trinity-large-preview:freeTrinity Large Preview131K
arcee-ai/trinity-large-thinkingTrinity Large Thinking262K

Black Forest Labs​

Model IDNameContext
black-forest-labs/flux.2-flexFLUX.2 Flex67K
black-forest-labs/flux.2-klein-4bFLUX.2 Klein 4B40K
black-forest-labs/flux.2-maxFLUX.2 Max46K
black-forest-labs/flux.2-proFLUX.2 Pro46K

Bytedance Seed​

Model IDNameContext
bytedance-seed/seedream-4.5Seedream 4.54K

Cognitivecomputations​

Model IDNameContext
cognitivecomputations/dolphin-mistral-24b-venice-edition:freeUncensored (free)32K

Deepseek​

Model IDNameContext
deepseek/deepseek-r1-distill-llama-70bDeepSeek R1 Distill Llama 70B8K
deepseek/deepseek-chat-v3-0324DeepSeek V3 032416K
deepseek/deepseek-v3.1-terminusDeepSeek V3.1 Terminus131K
deepseek/deepseek-v3.1-terminus:exactoDeepSeek V3.1 Terminus (exacto)131K
deepseek/deepseek-v3.2DeepSeek V3.2163K
deepseek/deepseek-v3.2-specialeDeepSeek V3.2 Speciale163K
deepseek/deepseek-chat-v3.1DeepSeek-V3.1163K
deepseek/deepseek-r1DeepSeek: R164K

Google​

Model IDNameContext
google/gemini-2.0-flash-001Gemini 2.0 Flash1M
google/gemini-2.5-flashGemini 2.5 Flash1M
google/gemini-2.5-flash-liteGemini 2.5 Flash Lite1M
google/gemini-2.5-flash-lite-preview-09-2025Gemini 2.5 Flash Lite Preview 09-251M
google/gemini-2.5-flash-preview-09-2025Gemini 2.5 Flash Preview 09-251M
google/gemini-2.5-proGemini 2.5 Pro1M
google/gemini-2.5-pro-preview-05-06Gemini 2.5 Pro Preview 05-061M
google/gemini-2.5-pro-preview-06-05Gemini 2.5 Pro Preview 06-051M
google/gemini-3-flash-previewGemini 3 Flash Preview1M
google/gemini-3-pro-previewGemini 3 Pro Preview1M
google/gemini-3.1-flash-lite-previewGemini 3.1 Flash Lite Preview1M
google/gemini-3.1-pro-previewGemini 3.1 Pro Preview1M
google/gemini-3.1-pro-preview-customtoolsGemini 3.1 Pro Preview Custom Tools1M
google/gemma-2-9b-itGemma 2 9B8K
google/gemma-3-12b-itGemma 3 12B131K
google/gemma-3-12b-it:freeGemma 3 12B (free)32K
google/gemma-3-27b-itGemma 3 27B96K
google/gemma-3-27b-it:freeGemma 3 27B (free)131K
google/gemma-3-4b-itGemma 3 4B96K
google/gemma-3-4b-it:freeGemma 3 4B (free)32K
google/gemma-3n-e2b-it:freeGemma 3n 2B (free)8K
google/gemma-3n-e4b-itGemma 3n 4B32K
google/gemma-3n-e4b-it:freeGemma 3n 4B (free)8K
google/gemma-4-26b-a4b-itGemma 4 26B A4B262K
google/gemma-4-26b-a4b-it:freeGemma 4 26B A4B (free)262K
google/gemma-4-31b-itGemma 4 31B262K
google/gemma-4-31b-it:freeGemma 4 31B (free)262K

Inception​

Model IDNameContext
inception/mercury-2Mercury 2128K
inception/mercury-edit-2Mercury Edit 2128K

Liquid​

Model IDNameContext
liquid/lfm-2.5-1.2b-instruct:freeLFM2.5-1.2B-Instruct (free)131K
liquid/lfm-2.5-1.2b-thinking:freeLFM2.5-1.2B-Thinking (free)131K

Meta Llama​

Model IDNameContext
meta-llama/llama-3.2-11b-vision-instructLlama 3.2 11B Vision Instruct131K
meta-llama/llama-3.2-3b-instruct:freeLlama 3.2 3B Instruct (free)131K
meta-llama/llama-3.3-70b-instruct:freeLlama 3.3 70B Instruct (free)131K

Minimax​

Model IDNameContext
minimax/minimax-m1MiniMax M11M
minimax/minimax-m2MiniMax M2196K
minimax/minimax-m2.1MiniMax M2.1204K
minimax/minimax-m2.5MiniMax M2.5204K
minimax/minimax-m2.5:freeMiniMax M2.5 (free)204K
minimax/minimax-m2.7MiniMax M2.7204K
minimax/minimax-01MiniMax-011M

Mistralai​

Model IDNameContext
mistralai/codestral-2508Codestral 2508256K
mistralai/devstral-2512Devstral 2 2512262K
mistralai/devstral-medium-2507Devstral Medium131K
mistralai/devstral-small-2505Devstral Small128K
mistralai/devstral-small-2507Devstral Small 1.1131K
mistralai/mistral-medium-3Mistral Medium 3131K
mistralai/mistral-medium-3.1Mistral Medium 3.1262K
mistralai/mistral-small-3.1-24b-instructMistral Small 3.1 24B Instruct128K
mistralai/mistral-small-3.2-24b-instructMistral Small 3.2 24B Instruct96K
mistralai/mistral-small-2603Mistral Small 4262K

Moonshotai​

Model IDNameContext
moonshotai/kimi-k2Kimi K2131K
moonshotai/kimi-k2-0905Kimi K2 Instruct 0905262K
moonshotai/kimi-k2-0905:exactoKimi K2 Instruct 0905 (exacto)262K
moonshotai/kimi-k2-thinkingKimi K2 Thinking262K
moonshotai/kimi-k2.5Kimi K2.5262K

Nousresearch​

Model IDNameContext
nousresearch/hermes-3-llama-3.1-405b:freeHermes 3 405B Instruct (free)131K
nousresearch/hermes-4-405bHermes 4 405B131K
nousresearch/hermes-4-70bHermes 4 70B131K

Nvidia​

Model IDNameContext
nvidia/nemotron-3-nano-30b-a3b:freeNemotron 3 Nano 30B A3B (free)256K
nvidia/nemotron-3-super-120b-a12bNemotron 3 Super262K
nvidia/nemotron-3-super-120b-a12b:freeNemotron 3 Super (free)262K
nvidia/nemotron-nano-12b-v2-vl:freeNemotron Nano 12B 2 VL (free)128K
nvidia/nemotron-nano-9b-v2:freeNemotron Nano 9B V2 (free)128K
nvidia/nemotron-nano-9b-v2nvidia-nemotron-nano-9b-v2131K

Openai​

Model IDNameContext
openai/gpt-oss-120bGPT OSS 120B131K
openai/gpt-oss-120b:exactoGPT OSS 120B (exacto)131K
openai/gpt-oss-20bGPT OSS 20B131K
openai/gpt-oss-safeguard-20bGPT OSS Safeguard 20B131K
openai/gpt-4.1GPT-4.11M
openai/gpt-4.1-miniGPT-4.1 Mini1M
openai/gpt-4o-miniGPT-4o-mini128K
openai/gpt-5GPT-5400K
openai/gpt-5-chatGPT-5 Chat (latest)400K
openai/gpt-5-codexGPT-5 Codex400K
openai/gpt-5-imageGPT-5 Image400K
openai/gpt-5-miniGPT-5 Mini400K
openai/gpt-5-nanoGPT-5 Nano400K
openai/gpt-5-proGPT-5 Pro400K
openai/gpt-5.1GPT-5.1400K
openai/gpt-5.1-chatGPT-5.1 Chat128K
openai/gpt-5.1-codexGPT-5.1-Codex400K
openai/gpt-5.1-codex-maxGPT-5.1-Codex-Max400K
openai/gpt-5.1-codex-miniGPT-5.1-Codex-Mini400K
openai/gpt-5.2GPT-5.2400K
openai/gpt-5.2-chatGPT-5.2 Chat128K
openai/gpt-5.2-proGPT-5.2 Pro400K
openai/gpt-5.2-codexGPT-5.2-Codex400K
openai/gpt-5.3-codexGPT-5.3-Codex400K
openai/gpt-5.4GPT-5.41M
openai/gpt-5.4-miniGPT-5.4 Mini400K
openai/gpt-5.4-nanoGPT-5.4 Nano400K
openai/gpt-5.4-proGPT-5.4 Pro1M
openai/gpt-oss-120b:freegpt-oss-120b (free)131K
openai/gpt-oss-20b:freegpt-oss-20b (free)131K
openai/o4-minio4 Mini200K

Openrouter​

Model IDNameContext
openrouter/elephant-alphaElephant (free)262K
openrouter/freeFree Models Router200K

Prime Intellect​

Model IDNameContext
prime-intellect/intellect-3Intellect 3131K

Qwen​

Model IDNameContext
qwen/qwen-2.5-coder-32b-instructQwen2.5 Coder 32B Instruct32K
qwen/qwen2.5-vl-72b-instructQwen2.5 VL 72B Instruct32K
qwen/qwen3-235b-a22b-07-25Qwen3 235B A22B Instruct 2507262K
qwen/qwen3-235b-a22b-thinking-2507Qwen3 235B A22B Thinking 2507262K
qwen/qwen3-30b-a3b-instruct-2507Qwen3 30B A3B Instruct 2507262K
qwen/qwen3-30b-a3b-thinking-2507Qwen3 30B A3B Thinking 2507262K
qwen/qwen3-coderQwen3 Coder262K
qwen/qwen3-coder:exactoQwen3 Coder (exacto)131K
qwen/qwen3-coder-30b-a3b-instructQwen3 Coder 30B A3B Instruct160K
qwen/qwen3-coder-flashQwen3 Coder Flash128K
qwen/qwen3-maxQwen3 Max262K
qwen/qwen3-next-80b-a3b-instructQwen3 Next 80B A3B Instruct262K
qwen/qwen3-next-80b-a3b-thinkingQwen3 Next 80B A3B Thinking262K
qwen/qwen3.5-397b-a17bQwen3.5 397B A17B262K
qwen/qwen3.5-plus-02-15Qwen3.5 Plus 2026-02-151M
qwen/qwen3.6-plusQwen3.6 Plus1M
qwen/qwen3.5-flash-02-23Qwen: Qwen3.5-Flash1M

Sourceful​

Model IDNameContext
sourceful/riverflow-v2-fast-previewRiverflow V2 Fast Preview8K
sourceful/riverflow-v2-max-previewRiverflow V2 Max Preview8K
sourceful/riverflow-v2-standard-previewRiverflow V2 Standard Preview8K

Stepfun​

Model IDNameContext
stepfun/step-3.5-flashStep 3.5 Flash256K

X Ai​

Model IDNameContext
x-ai/grok-3Grok 3131K
x-ai/grok-3-betaGrok 3 Beta131K
x-ai/grok-3-miniGrok 3 Mini131K
x-ai/grok-3-mini-betaGrok 3 Mini Beta131K
x-ai/grok-4Grok 4256K
x-ai/grok-4-fastGrok 4 Fast2M
x-ai/grok-4.1-fastGrok 4.1 Fast2M
x-ai/grok-4.20-betaGrok 4.20 Beta2M
x-ai/grok-4.20-multi-agent-betaGrok 4.20 Multi - Agent Beta2M
x-ai/grok-code-fast-1Grok Code Fast 1256K

Xiaomi​

Model IDNameContext
xiaomi/mimo-v2-flashMiMo-V2-Flash262K
xiaomi/mimo-v2-omniMiMo-V2-Omni262K
xiaomi/mimo-v2-proMiMo-V2-Pro1M

Z Ai​

Model IDNameContext
z-ai/glm-4.5GLM 4.5128K
z-ai/glm-4.5-airGLM 4.5 Air128K
z-ai/glm-4.5-air:freeGLM 4.5 Air (free)128K
z-ai/glm-4.5vGLM 4.5V64K
z-ai/glm-4.6GLM 4.6200K
z-ai/glm-4.6:exactoGLM 4.6 (exacto)200K
z-ai/glm-4.7GLM-4.7204K
z-ai/glm-4.7-flashGLM-4.7-Flash200K
z-ai/glm-5GLM-5202K
z-ai/glm-5-turboGLM-5-Turbo202K
z-ai/glm-5.1GLM-5.1202K

Setup​

1. Get API Key​

  1. Visit OpenRouter
  2. Create or log in to your account
  3. Go to Keys → Create Key
  4. Copy the key

2. Add to Clawrium​

clm provider add my-router --type openrouter

You will be prompted to enter your API key securely.

3. Select Model​

Choose from OpenRouter's extensive model list:

  • anthropic/claude-opus-4 (best quality)
  • google/gemini-2.5-pro (competitive pricing)
  • openai/gpt-4o (familiar API)

Configuration​

# View provider details
clm provider list

# Change default model
clm provider edit my-router --model anthropic/claude-sonnet-4

# Update API key
clm provider edit my-router --update-key

# Remove provider
clm provider remove my-router

Benefits​

  • Model fallback: Automatically route to available models
  • Unified billing: One account for multiple providers
  • Competitive pricing: Often cheaper than direct provider access
  • Model variety: Access to open-source and proprietary models

Pricing​

OpenRouter adds a small fee on top of provider costs. Check OpenRouter pricing for current rates.

Usage in Agents​

During agent onboarding:

clm agent configure my-agent
# Select my-router when prompted for provider

Model Routing​

You can switch models without changing providers:

clm provider edit my-router --model deepseek/deepseek-chat-v3

Then restart your agent to use the new model.

Troubleshooting​

"Model not available"

  • Check OpenRouter model status page
  • Some models may have temporary outages
  • Try a fallback model

"Credits exhausted"

  • Add credits in OpenRouter dashboard
  • Set up auto-recharge for production use

Back to Providers