> ## Documentation Index
> Fetch the complete documentation index at: https://docs.portkey.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Errors

The Prisma AIRS AI Gateway uses conventional response codes to indicate the success or failure of an API request. In general: Codes in the `2xx` range indicate success. Codes in the `4xx` range indicate an error that failed given the information provided. Codes in the `5xx` range indicate an error with the AI Gateway's servers (these are rare).

## Common Errors

During request processing, you may encounter error codes from either the AI Gateway or the LLM provider:

| Status Code | Description                                  | Source                     |
| ----------- | -------------------------------------------- | -------------------------- |
| `408`       | Request timed out                            | The AI Gateway OR Provider |
| `412`       | Budget exhausted                             | The AI Gateway OR Provider |
| `429`       | Request rate limited                         | The AI Gateway OR Provider |
| `446`       | Guardrail checks failed (request denied)     | The AI Gateway             |
| `246`       | Guardrail checks failed (request successful) | The AI Gateway             |

<Note>
  Provider-specific error codes are passed through by the AI Gateway. For debugging these errors, refer to our [Error Library](https://portkey.ai/error-library).
</Note>


## Related topics

- [Errors](/docs/aigw/api-reference/admin-api/error.md)
- [Common Errors & Resolutions](/docs/aigw/support/common-errors-and-resolutions.md)
- [Get analytics graphs errors](/docs/aigw/api-reference/analytics/graphs/get-analytics-graphs-errors.md)
- [Get analytics graphs errors rate](/docs/aigw/api-reference/analytics/graphs/get-analytics-graphs-errors-rate.md)
- [Get analytics graphs errors stacks](/docs/aigw/api-reference/analytics/graphs/get-analytics-graphs-errors-stacks.md)