Errors & limits
Errors follow the OpenAI error shape: an error object with message, type and code fields, plus a conventional HTTP status.
| Status | Meaning |
|---|---|
| 400 | Bad request — a parameter is malformed or missing. The body explains which. |
| 401 | Missing or invalid API key. |
| 402 | Insufficient balance — top up and retry. |
| 404 | Unknown model slug or endpoint. |
| 408 | Upstream timeout — safe to retry; you are not billed for failed generations. |
| 429 | Rate limited — back off and retry. Limits scale with account history. |
| 502 / 503 | Upstream provider error — the gateway retries automatically across providers; persistent failures are safe to retry. |
Rate limits
Default limits are generous for development and rise automatically with sustained usage. If you are planning a burst — batch jobs, launches, evals — contact us and we will raise the ceiling ahead of time.