API Documentation
Quick integration guide and complete API reference
Errors
Identify the error type before changing settings
Most integration failures can be narrowed down from the HTTP status code first. For a first debug pass, check the API key, model ID, quota, and request URL before changing multiple settings at once.
If the error response includes a request_id, keep it and include it when contacting us so we can locate the issue.
Start with these checks
Authentication failed
Check that Authorization uses the Bearer sk-xxxx format, that the API key was copied completely, and that the key is still valid.
Model not found
Check that the model field contains a real callable model ID. Do not use only a vendor name, capability label, or placeholder.
Insufficient quota
Check account balance, token quota limits, promotional request benefits, and whether the request exceeds available quota.
Too many requests
Reduce concurrency or request frequency. Avoid retry loops that run without a limit.
Find the issue you are seeing
I see authentication failed, unauthorized, or 401. What should I check first?
I see model not found or 404. How should I fix it?
I see insufficient quota or 402. Where should I look?
I see too many requests or 429. Should I keep retrying?
| HTTP | Error Type | Description |
|---|---|---|
| 400 | invalid_request_error | Invalid request parameters or missing required fields. |
| 401 | authentication_error | Token is missing, invalid, or expired. |
| 402 | insufficient_quota | Quota is insufficient, or promotional request benefits are exhausted and paid billing cannot continue. |
| 404 | model_not_found | Model does not exist or currently has no active bound channel. |
| 429 | rate_limit_error | Rate limit exceeded. |
| 500 | server_error | Internal platform error. Please contact us. |
