overloaded

Response

Every failure uses this envelope. credits_charged is 0. The message below is the default text for this code. Live messages can change, so branch on error.code.

1{2  "ok": false,3  "error": {4    "code": "overloaded",5    "message": "This endpoint's queue is full, or this account has too many requests in progress at once; retry with backoff. Never charged.",6    "retryable": true7  },8  "credits_charged": 0,9  "request_id": "req_0123456789abcdef01234567"10}

This code sends retry-after: 2.

When it happens

• This endpoint's queue is full.
• This account has a very large number of requests in progress at once. The request is refused before anything is charged.
• A duplicate Idempotency-Key while the first attempt is still running is also this code, with the message a request with this Idempotency-Key is still running; retry shortly.

What to do

• The response includes retry-after: 2. Wait, then retry. The attempt is free.

The response header x-request-id matches request_id. The full list is on errors.