Errors & limits

The API uses conventional HTTP status codes and returns errors in OpenAI’s format.

Error format

{
  "error": {
    "message": "A human-readable description of what happened.",
    "type": "invalid_request_error",
    "code": "..."
  }
}

Status	Meaning	How to fix
`400 Bad Request`	Invalid body (malformed JSON, missing parameter)	Check `model` and `messages`/`input`
`401 Unauthorized`	Key missing, invalid, or revoked	Check the `Authorization` header — see Authentication
`403 Forbidden`	Model not enabled on your plan	Use a model from your plan or upgrade
`404 Not Found`	Endpoint or model does not exist	Check the URL and the model `id`
`429 Too Many Requests`	Requests/min limit reached	Slow down, apply backoff, or upgrade your plan
`5xx`	Temporary server error	Retry with exponential backoff

Each plan has a requests-per-minute limit (fair-use). When you exceed it, the API responds with 429.