{"uid":"cap_kgdBNcA8XwSGvMm3iz11Z","slug":"baseten-model-apis-baseten-chat-completions-bb3148ca","name":"Baseten Chat Completions","description":"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.","url":"https://mpp.orthogonal.com/baseten/v1/chat/completions?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":null,"responseSchema":null,"example":null,"exampleRequest":null,"tags":["inference","llm","models","gpu","ai","compute"],"displayCostAmount":"0.003686","displayCostAsset":"USDC","priceDynamic":true,"priceHint":null,"priceStatus":"priced","priceSource":"settled","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"dynamic","summary":"$0.003686/call","primary":{"kind":"dynamic","protocol":"mpp","network":"tempo","amountUsd":null,"per":"call","confidence":"unknown"},"accepted":[{"kind":"dynamic","protocol":"mpp","network":"tempo","amountUsd":null,"per":"call","confidence":"unknown"}]},"paymentMethods":[{"uid":"pm__h95-j64tSw42R3UcjFFw","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"unknown","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":"Baseten Model APIs","brandSlug":"baseten-model-apis-mpp","brandBaseUrl":"https://inference.baseten.co","brandDocsUrl":"https://inference.baseten.co","whatItDoes":"Send a multi-turn conversation to an open-source LLM on Baseten and receive a generated text completion via an OpenAI-compatible interface","exampleAgentPrompt":"Using the Baseten inference API, send this conversation to the model and get a completion back: system prompt is 'You are a helpful assistant', and the user message is 'Explain the difference between supervised and unsupervised learning in two sentences'.","exampleUseCases":null,"resultDescription":"Returns an OpenAI-compatible chat completion response object containing the assistant's generated message, the model used, token usage statistics (prompt tokens, completion tokens, total tokens), and a finish reason indicating how the generation ended.","failureModes":["Invalid or unsupported model ID returns a 404 or error response","Malformed messages array causes a 400 bad request","Exceeding context window length results in a truncation or error","Authentication failure returns a 401 unauthorized","Rate limiting or GPU capacity issues may return a 429 or 503","Network timeout for very long completions"],"whenToPreferThis":"Choose this endpoint when you need an OpenAI-compatible chat completions interface backed by open-source LLMs on a high-performance GPU inference platform. Ideal when you want a drop-in replacement for the OpenAI API, need to run models like Llama or Mistral without vendor lock-in, or want predictable per-call pricing on a curated inference backend.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-10T00:56:53.771Z","isFirstParty":false,"canonicalSlug":"baseten-model-apis-baseten-chat-completions-bb3148ca"}