Errors

Errors use standard HTTP status codes and an OpenAI-style body:

{
  "error": {
    "message": "Invalid API key.",
    "type": "authentication_error",
    "code": "invalid_api_key"
  }
}

Status codes

Status	Meaning	What to do
400	The request is malformed or a parameter is invalid.	Fix the request; the message says which field.
400 context_length_exceeded	The prompt plus max_tokens is longer than the model’s context.	Shorten the input or lower max_tokens.
401	Missing or invalid API key.	Check the Authorization header and the key.
402	Not enough credits.	Add credits in the dashboard.
404	Unknown model or endpoint.	Check the model ID with List models.
429	Too many concurrent requests, or the model is under heavy load.	Wait a moment and retry with backoff. See Rate limits.
500	Unexpected error on our side.	Retry with backoff.
503	Temporarily over capacity.	Retry with backoff.

Retrying

Retry 429, 500 and 503 with exponential backoff and jitter, for example 1, 2, 4 and 8 seconds. Do not retry 400, 401, 402 or 404 without changing the request. The OpenAI SDKs already retry these twice by default. Set max_retries to change that.