Error Codes
Stable HTTP status and business error code mappings used by gpt88.cc for client-side retry and troubleshooting logic.
Error envelope
error envelopejson
{
"error": {
"type": "rate_limit_error",
"code": "rate_limit_exceeded",
"message": "Rate limit exceeded for model gpt-5.6-sol",
"param": null,
"request_id": "req_01HZX3..."
}
}Common codes
| HTTP | code | meaning |
|---|---|---|
| 400 | invalid_request_error | Malformed request body or invalid field shape. |
| 401 | invalid_api_key | Missing, revoked, or invalid API key. |
| 403 | permission_denied | The current key cannot access the requested model or endpoint. |
| 404 | model_not_found | Model ID does not exist or is not available to the key. |
| 408 | request_timeout | The upstream response exceeded the gateway timeout window. |
| 429 | rate_limit_exceeded | Rate limit was hit at account, key, or model level. |
| 429 | insufficient_quota | Balance or quota is exhausted. |
| 500 | internal_error | Gateway or upstream internal failure. |
| 502 | upstream_error | Unexpected upstream provider response. |
| 503 | service_unavailable | Upstream capacity is temporarily unavailable. |
| 504 | gateway_timeout | Gateway timed out while waiting for upstream. |