DEVELOPER DOCUMENTATION
Errors & limits
Handle errors deliberately. Keep retries bounded.
| HTTP | Meaning | Next step |
|---|---|---|
| 400 | Invalid request | Check the exact model ID, text messages, and supported parameters. |
| 401 | Invalid or revoked key | Check your key and selected gateway. |
| 402 | Insufficient available allowance | Check your selected funding source, available balance, API-key limit, and pending reservations. |
| 404 | No available route | Refresh the live catalog; the model may no longer be available. |
| 429 | Rate limit reached | Back off before retrying. |
| 502 / 503 | Upstream or service unavailable | Retry with bounded exponential backoff; inspect any receipt first. |
Request limits
Maximum output is 65,536 tokens at the gateway and may be capped further by available credits or upstream limits. The model’s catalog context and output limits do not override the gateway’s request contract. There is currently no per-user or per-key limit on chat requests per minute or simultaneous chats. Each request requires sufficient credit; sponsored free models have a separate daily allowance.