Skip to content
Docs

Chat Completions

OpenAI-compatible endpoint for chat-based text generation.

Endpoint

http
1POST /v1/chat/completions2Content-Type: application/json

Request example

json
1{2  "model": "gpt-5.2",3  "messages": [4    {5      "role": "system",6      "content": "You are a helpful assistant."7    },8    {9      "role": "user",10      "content": "Write a haiku about observability."11    }12  ]13}

Streaming

Set stream: true to receive Server-Sent Events. Usage metrics may arrive at the end of the stream.

Tip
Log pages show input / cached / output tokens when available.