Requests, responses & errors

The gateway returns OpenAI-compatible structures. Platform-specific fields such as request_id are delivered as response headers.

Success response

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "choices": [
    { "index": 0, "message": { "role": "assistant", "content": "..." }, "finish_reason": "stop" }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 34,
    "total_tokens": 46
  }
}

Unified error format

{
  "error": {
    "message": "...",
    "type": "...",
    "code": "...",
    "param": null,
    "request_id": "req_..."
  }
}

Error codes

See the error code reference for the full list and billing semantics.