Error Codes

{
  "error": "Invalid request format"
}

{
  "error": "Invalid or missing API key"
}

{
  "error": "Insufficient operational platform credits on workspace ledger. Top up required."
}

{
  "error": "IP address not allowed. This workspace has an IP allowlist enabled."
}

{
  "error": "Route not found"
}

{
  "error": "Request body too large"
}

{
  "error": "Rate limit exceeded: Workspace RPM Limit (global)",
  "limit": 100,
  "current": 101,
  "window": "fixed_minute",
  "rule_id": "abc123",
  "retry_after": 45
}

{
  "error": "Failed to create batch record",
  "type": "internal_error",
  "code": "BATCH_CREATE_FAILED"
}

{
  "error": "Malformed JSON response from provider",
  "type": "upstream_error",
  "code": "PROVIDER_CONNECTION_FAILED"
}

{
  "error": "All providers failed. Last error: 503 from openai",
  "type": "provider_error",
  "code": "ALL_PROVIDERS_FAILED"
}

{
  "error": {
    "message": "Invalid model specified",
    "type": "invalid_request_error",
    "param": "model",
    "code": "model_not_found"
  }
}

{
  "type": "error",
  "error": {
    "type": "invalid_request_error",
    "message": "Invalid model specified"
  }
}

{
  "error": {
    "code": 400,
    "message": "Invalid value",
    "status": "INVALID_ARGUMENT"
  }
}

interface ErrorResponse {
  error: string;           // Human-readable error message
  type?: string;           // Error category (e.g. "internal_error", "upstream_error")
  code?: string;           // Machine-readable error code
  limit?: number;          // Rate limit maximum (429 only)
  current?: number;        // Current usage (429 only)
  window?: string;         // Time window type (429 only)
  retry_after?: number;    // Seconds to wait (429 only)
  rule_id?: string;        // Rate limit rule ID (429 only)
}