Catalog

Models & pricing

All models enabled on TokRouter, with their API identifier and price in credits per million tokens.

API rate limit

60 requests per minute maximum, per API key, on /api/v1/chat/completions and /api/v1/messages.

ModelAPI identifierCategoryContextInput price (credits/M)Output price (credits/M)Fixed fee/req.Free
Olmo 3 32B Thinkallenai/olmo-3-32b-thinkAutre65,5360.1650.550.0020Available
Claude Haiku 4.5anthropic/claude-haiku-4.5Claude200,0002.006.000.0020
Claude Opus 4.8anthropic/claude-opus-4.8Claude1,000,0006.0030.000.0020
Claude Sonnet 5anthropic/claude-sonnet-5Claude1,000,0004.0012.000.0020
Claude Opus 5anthropic/claude-opus-5Claude1,000,0005.5027.500.0020
DeepSeek V3deepseek/deepseek-chatAutre163,8400.28311.13160.0020Available
Gemini 2.5 Flashgoogle/gemini-2.5-flashGemini1,048,5760.332.750.0020
Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-liteGemini1,048,5760.110.440.0020Available
Gemini 2.5 Progoogle/gemini-2.5-proGemini1,048,5761.37511.000.0020
Gemini 3.5 Flashgoogle/gemini-3.5-flashGemini1,048,5761.659.900.0020
Nemotron 3 Ultranemotron-3-ultraAutre1,000,0000.000.100.0020
GPT-5.4openai/gpt-5.4GPT1,050,0003.0017.000.0020
GPT-5.4 Miniopenai/gpt-5.4-miniGPT400,0001.005.000.0020
GPT-5.5openai/gpt-5.5GPT1,050,0006.0033.000.0020
GPT-5.6 Lunaopenai/gpt-5.6-lunaGPT1,050,0000.110.660.0020
GPT-5.6 Solopenai/gpt-5.6-solGPT1,050,0005.5033.000.0020
GPT-5.6 Terragpt-5.6-terraGPT1,050,0001.106.600.0020
Qwen3 Coder (480B)qwen/qwen3-coderAutre1,048,5761.001.000.0020
Venicecognitivecomputations/dolphin-mistral-24b-venice-editionAutre128,0000.220.990.0020
GLM 4.7GLM-4.7GLM204,8000.441.9250.0020

Indicative prices in credits per 1,000,000 tokens (1 credit = 1 USD billed). Actual billing uses each model's exact cost, generally identical to these values.