POST /v1/chat/completions

Request

curl https://api.model-gate.com/v1/chat/completions \
  -H "Authorization: Bearer mg_live_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "ch-47",
    "messages": [
      {"role": "user", "content": "Explain this API in one sentence."}
    ],
    "stream": false
  }'

The model can be a canonical ID or an enabled alias. Model Gate resolves aliases before pricing and sends the canonical ID upstream.

Response

{
  "id": "chatcmpl_example",
  "object": "chat.completion",
  "model": "claude-opus-4.7",
  "choices": [
    {
      "index": 0,
      "message": {"role": "assistant", "content": "Model Gate provides one compatible API for multiple AI models."},
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 14,
    "completion_tokens": 17,
    "total_tokens": 31
  }
}

Streaming request

Set "stream": true. The upstream Server-Sent Events are passed through without rewriting successful event payloads.

Asynchronous request

For supported endpoints, add "async": true with "stream": false. The immediate response is HTTP 202 and contains request_id and a Partner API result URL.

Errors

Provider non-2xx status, body, and content type are passed through unchanged. Locally generated validation errors use the Model Gate error envelope.

Status	Meaning	Action
400	Invalid request	Check the request body and model ID.
401	Invalid or frozen key	Verify or rotate the API key.
429	Rate or concurrency limit exceeded	Respect Retry-After and retry with backoff.
5xx	Temporary upstream or gateway error	Retry idempotent requests with exponential backoff.