{"openapi":"3.1.0","info":{"title":"Baseten Model APIs","version":"1.0.0","description":"Baseten is a high-performance inference platform for running open source LLMs. This API provides an OpenAI-compatible chat completions endpoint, so it works as a drop-in replacement with any OpenAI SDK or client. Just swap the base URL and API key.\n\nAvailable models include DeepSeek V3 and V3.1, GLM 4.6 and 4.7 from Zhipu, Moonshot's Kimi K2 family (including K2 Thinking with 262k context), and OpenAI's GPT OSS 120B. Several models support controllable reasoning depth via a reasoning_effort parameter.\n\nSupports streaming, tool calling, structured outputs, and extended context windows up to 262k tokens."},"x-service-info":{"name":"Baseten Model APIs","docs":{"llms":"https://api.orthogonal.com/llms.txt"},"protocols":["mpp","x402","np"]},"servers":[{"url":"https://mpp.orthogonal.com/baseten","description":"MPP (Tempo) rail"},{"url":"https://x402.orthogonal.com/baseten","description":"x402 rail"},{"url":"https://np.orthogonal.com/baseten","description":"np (Circle Gateway, x402 v2) rail"}],"paths":{"/v1/chat/completions":{"post":{"operationId":"baseten_POST__v1_chat_completions","summary":"Send a conversation to a model and get a completion back. Works exactly like the OpenAI chat completions endpoint. Pass messages and a model slug, get a response with the assistant's reply. Supports streaming for real-time token delivery, tool calling for function execution, structured outputs via response_format, and controllable reasoning depth on supported models.","tags":["Baseten Model APIs"],"responses":{"200":{"description":"Successful response"},"402":{"description":"Payment Required (x402 / MPP / np)"}},"x-payment-info":{"price":"dynamic","offers":[{"method":"mpp","intent":"charge","rail":"tempo","currency":"USDC.e","url":"https://mpp.orthogonal.com/baseten/v1/chat/completions"},{"method":"x402","intent":"charge","rail":"base","currency":"USDC","url":"https://x402.orthogonal.com/baseten/v1/chat/completions"},{"method":"np","intent":"charge","rail":"base","currency":"USDC","settlement":"circle-gateway","version":"x402-v2","url":"https://np.orthogonal.com/baseten/v1/chat/completions"}]}}},"/v1/models":{"get":{"operationId":"baseten_GET__v1_models","summary":"Returns the current list of available models with metadata including pricing, context window sizes, and supported features. Use this to discover valid model slugs for the chat completions endpoint.","tags":["Baseten Model APIs"],"responses":{"200":{"description":"Successful response"}}}}}}