📋 Status Code Reference
| Status Code | Explanation |
|---|---|
| 400 Bad Request | The request format is incorrect or cannot be understood by the server, typically indicating a client-side error. Check your request format — for example, o1-series models do not support the system parameter. |
| 401 Unauthorized (Invalid token) | API key authentication failed. Verify that your API key is correct; other causes include expired tokens. Try switching to a different model to verify whether your API key is valid. If a different model works normally, contact your administrator. |
| 403 Forbidden / Token group XXX is disabled | Usually caused by insufficient permissions, token permission issues, or token quota exhausted. Edit the token to remove quota limits, or create a new token. |
| 404 Not Found | The requested resource was not found. You may be trying to access a non-existent endpoint. Check that the Base URL is correct — try appending /v1 or a trailing slash /. |
| 413 Request Entity Too Large | The request body is too large. Your prompt may be too long. Shorten the prompt and try again to confirm whether it can be called normally. |
| 429 Too Many Requests / Current group upstream load saturated | You have exceeded your rate limit due to frequent requests. OpenAI rate-limits individual accounts; a 429 indicates that a backend account has hit its concurrency limit. Please try again. |
| 500 Internal Server Error | An internal server error occurred. This may be an issue with the relay server or OpenAI's servers — not your problem. Try again; if the error persists, contact your administrator. |
| 503 Service Unavailable / No available channel for model xxxx in group NNN | The server is temporarily unavailable, possibly due to OpenAI maintenance or server overload, or a backend channel management issue. Contact your administrator to have the model added. Try again; if the error persists, contact your administrator. |
| 504 Gateway Timeout | The gateway timed out — no response was received from the upstream server within the allotted time. Try again; if the error persists, contact your administrator. |
| 524 Connection Timeout | The server did not complete the request within the allotted time, possibly due to API channel congestion. Try again; if the error persists, contact your administrator. |
The above is only a partial list of HTTP status codes. Some status codes may vary depending on the server's implementation and usage.