Reasoning LLM API

Extended-thinking models for math, planning and hard coding problems, with reasoning effort passed through where the provider supports it.

Reasoning LLM API models and pricing

ModelProviderContextPrice
Qwen 3.8 Max (0902) qwen/qwen3.8-max-0902Qwen1M$2.00 in / $6.00 out per 1M tokens
Claude Fable 5.1 claude-fable-5-1Anthropic1M$10.00 in / $50.00 out per 1M tokens
Claude Fable 5 claude-fable-5Anthropic1M$10.00 in / $50.00 out per 1M tokens
Claude Opus 5.5 claude-opus-5-5Anthropic1M$4.00 in / $20.00 out per 1M tokens
Claude Opus 5 claude-opus-5Anthropic1M$5.00 in / $25.00 out per 1M tokens
Claude Opus 4.8 claude-opus-4-8Anthropic1M$5.00 in / $25.00 out per 1M tokens
Muse Spark 1.3 muse-spark-1.3Meta1M$1.25 in / $4.25 out per 1M tokens
Claude Opus 4.7 claude-opus-4-7Anthropic200K$5.00 in / $25.00 out per 1M tokens
Claude Sonnet 5.5 claude-sonnet-5-5Anthropic1M$2.00 in / $10.00 out per 1M tokens
Claude Sonnet 5 claude-sonnet-5Anthropic1M$2.00 in / $10.00 out per 1M tokens
Jev Router typesafe/jev-routerTypeSafe1M$1.25 in / $4.25 out per 1M tokens
Claude Haiku 5.5 claude-haiku-5-5Anthropic1M$0.10 in / $0.50 out per 1M tokens
Qwen 3.8 27B runanywhere/qwen3.8-27bRunAnywhere256K$0.20 in / $2.50 out per 1M tokens
GLM-5.3 Flash runanywhere/glm-5.3-flashRunAnywhere1M$0.10 in / $0.35 out per 1M tokens
Muse Spark 1.3 Contributor muse-spark-1.3-contributorMeta1M$0.10 in / $0.20 out per 1M tokens
Claude Opus 4.6 claude-opus-4-6Anthropic200K$5.00 in / $25.00 out per 1M tokens
DeepSeek V4.1 Flash deepseek-v4-flashDeepSeek1M$0.15 in / $0.60 out per 1M tokens
Qwen 3.8 Flash qwen/qwen3.8-flashQwen1M$0.15 in / $0.47 out per 1M tokens
Qwen 3.8 27B cerebras/qwen-3.8-27bCerebras128K$0.99 in / $1.49 out per 1M tokens
GPT-6 Sol gpt-6-solOpenAI1.05M$2.00 in / $10.00 out per 1M tokens
GPT-6 Luna gpt-6-lunaOpenAI1.05M$0.10 in / $0.50 out per 1M tokens
GPT-5.5 gpt-5.5OpenAI1.05M$5.00 in / $30.00 out per 1M tokens
GPT-5.4 gpt-5.4OpenAI1.05M$2.50 in / $15.00 out per 1M tokens
Gemini 3.7 Flash gemini-3.7-flashGoogle1M$0.75 in / $3.75 out per 1M tokens
Gemini Latest gemini-latestGoogle1M$0.75 in / $3.75 out per 1M tokens
Grok 4.7 grok-4.7xAI500K$2.00 in / $6.00 out per 1M tokens
DeepSeek V4 Pro deepseek-v4-proDeepSeek1M$0.435 in / $0.87 out per 1M tokens
Qwen 3.8 Max qwen/qwen3.8-maxQwen1M$2.00 in / $6.00 out per 1M tokens
Qwen 3.8 Max or/qwen3.8-maxOpenRouter1M$2.00 in / $6.00 out per 1M tokens
GPT-6.1 Sol gpt-6.1-solOpenAI1.05M$2.00 in / $10.00 out per 1M tokens
GPT-6.1 Terra gpt-6.1-terraOpenAI1.05M$1.00 in / $5.00 out per 1M tokens
GPT-5.6 gpt-5.6OpenAI1.05M$2.00 in / $12.00 out per 1M tokens
GPT-5.6 Sol gpt-5.6-solOpenAI1.05M$4.00 in / $20.00 out per 1M tokens
GPT-5.6 Terra gpt-5.6-terraOpenAI1.05M$2.00 in / $12.00 out per 1M tokens
GPT-5.6 Luna gpt-5.6-lunaOpenAI1.05M$0.20 in / $1.20 out per 1M tokens
GPT-5.4 Mini gpt-5.4-miniOpenAI400K$0.75 in / $4.50 out per 1M tokens
Gemini 3.8 Flash gemini-3.8-flashGoogle1M$0.75 in / $3.75 out per 1M tokens
Gemini 3.5 Flash gemini-3.5-flashGoogle1M$0.75 in / $3.75 out per 1M tokens
Grok 4.6 grok-4.6xAI500K$2.00 in / $6.00 out per 1M tokens
Grok 4.5 grok-4.5xAI500K$2.00 in / $6.00 out per 1M tokens

FAQ

Is it compatible with the OpenAI SDK?

Yes. Set base_url to https://openpaths.io/v1 and use your OpenPaths API key; request and response shapes follow the OpenAI API.

How do I set reasoning effort?

Send reasoning_effort in the request body; it is forwarded to providers that support it.

How is it priced?

Prepaid, pay-as-you-go credits at close to provider list price with no subscription. The tables on this page are generated from the live OpenPaths model catalog.

Chat Completions Coding LLM API Free LLM API