Error Handling

Errors are returned as JSON with an error object containing message, type, and code.

Error response

{
  "error": {
    "message": "Rate limit exceeded. Please retry after a brief wait.",
    "type": "rate_limit_error",
    "code": 429
  }
}

HTTP Status Codes

Status	Type	Description
200	Success	Request succeeded.
400	invalid_request_error	Invalid request body, missing messages, or content filtered by safety system.
401	authentication_error	Invalid or missing API key.
429	rate_limit_error	Too many requests or concurrent connections. Check the `Retry-After` header.
502	upstream_error	Failed to connect to upstream model provider.
503	service_unavailable	Service temporarily unavailable. Daily quota or plan limit reached.

Retry Strategy

For 429 errors, respect the Retry-After header value (in seconds). For 503 errors, use exponential backoff starting from 5 seconds with a maximum of 60 seconds.