Qloud Docs

Errors

Error codes, what they mean, and which to retry.

Errors use the OpenAI error shape:

{
  "error": {
    "message": "Human-readable description",
    "type": "rate_limit_exceeded",
    "code": "rate_limit_exceeded",
    "request_id": "qlo-..."
  }
}
StatusCodeMeaning
400invalid_requestThe request is malformed or uses an unsupported option.
400context_length_exceededThe prompt and requested output exceed the model's context window.
401authentication_errorThe API key is missing, invalid or revoked.
402insufficient_creditsYour credit cannot cover this request. Add credit in the dashboard.
403permission_deniedThe key or organization is not allowed to do this.
404model_not_foundThe model id is unknown. Ids are case-sensitive.
413payload_too_largeThe request body is over the size limit.
429rate_limit_exceededToo many requests or tokens for this key, or the daily spend limit was reached.
502upstream_errorThe model could not be served.
503model_unavailableThe model is temporarily unavailable.
504timeoutThe request took too long.

Retrying

Retry 429, 502, 503 and 504 with exponential backoff and jitter, honouring retry-after when present. Do not retry other 4xx errors without changing the request.

Getting help

Email hello@qloud.sh with the x-qlo-request-id, the time, the model id and the status code. Never send an API key.

On this page