Errors & limits
Make failures understandable and give your application a useful recovery path.
Common responses
| Status | Meaning | Next step |
|---|---|---|
| 400 | The request does not match the supported API. | Check the model, message content, and parameters. |
| 401 | Authentication failed. | Check the key and bearer header. |
| 429 | An account request or concurrency limit was reached. | Reduce concurrent work and respect retry guidance. |
| 503 | Capacity or a required dependency is unavailable. | Inspect the error code and Retry-After. |
No available provider
no_provider_available means no free matching provider can serve your selected model now. request_capacity means Router’s global request capacity is full. Both return 503.
Input and output limits
The API enforces model-specific limits alongside request size and concurrency limits. Discover the edition’s configured limits before sending long prompts. Unsupported generation parameters are rejected explicitly.
Usage is a measurement
Token counts are provider-reported operational measurements. Missing usage is not zero, and these measurements are not a billing ledger.