Error Codes
HTTP Status Codes
| Status | Meaning | Action |
|---|---|---|
| 200 | Success | — |
| 400 | Bad request | Check your request parameters |
| 401 | Unauthorized | Verify your API key |
| 403 | Forbidden | Check your account permissions |
| 404 | Not found | Verify the endpoint or model ID |
| 429 | Rate limit exceeded | Slow down or upgrade tier |
| 500 | Server error | Retry after a brief wait |
| 503 | Service unavailable | Retry after a brief wait |
Error Types
| Type | Description |
|---|---|
invalid_request_error | Malformed request or invalid parameters |
authentication_error | Invalid or missing API key |
rate_limit_error | Exceeded your rate limit |
model_not_found_error | Specified model doesn't exist |
context_length_exceeded | Input exceeds model's context window |
content_filter_error | Content blocked by safety policies |
server_error | Internal server error |
Error Response Format
{
"error": {
"message": "Human-readable description",
"type": "error_type",
"code": "error_code",
"param": "parameter_name"
}
}Common Errors
invalid_api_key
Status: 401
Message: "Invalid API key provided"Contact support@linkwo.com to verify your API key.
context_length_exceeded
Status: 400
Message: "This model's maximum context length is 128000 tokens"Reduce your input length or use max_tokens to limit output.
rate_limit_exceeded
Status: 429
Message: "Rate limit exceeded"Implement exponential backoff. See Rate Limits.
model_not_found
Status: 404
Message: "Model 'gpt-5' not found"Check available models at Model Overview.
Related
- Rate Limits — Rate limit details
- API Endpoints — Available endpoints