---
title: Ask AI Errors Reference
---

This is a reference to error codes and their definitions that can be returned from the Ask AI Chat.

## General API errors

---

### UNAUTHORIZED

There was an issue validating the auth token for the request.

### FORBIDDEN

Access to a resource is not available or not allowed for the requester.

> **Solution:** Make sure that your domain is [whitelisted](/docs/v4/askai-whitelisted-domains) and that you are using the correct `assistantId`.

### BAD_INPUT

The request included data that could either not be used to find a resource, or the data was malformed.

### TOO_MANY_ATTEMPTS

There have been too many requests made within a designated window. The requests are being rate limited.

> **Solution:** Wait for the rate limit window to pass and then try again.

## Ask AI chat errors

---

### AI_STREAM_ERROR

A general case error that occurred while communicating with the upstream provider. This could include stream processing issues, data corruption, or issues with the provider itself.

### AI_API_CALL

There was an issue specifically with communicating with the upstream provider.

> **Solution:** Check the provider's API status page(s) to see if they are experiencing any ongoing issues.

### AI_INVALID_API_KEY

The upstream provider reported that there was an issue with the supplied API key.

> **Solution:** Make sure to double-check that you are using the correct API key for your assistant; and that it has the correct permissions.

### AI_INSUFFICIENT_BALANCE

The upstream provider could not process the chat request due to a billing issue.

> **Solution:** You will need to log in to your provider’s dashboard to remedy this issue.

### AI_NO_TOOL

Ask AI could not call a specific tool.

> **Solution:** Be sure not to ask for any specific tool calls within your custom prompt. Ask AI has specific tools it uses to give the best results.

### AI_RETRY

There were too many failed attempts at communicating with the upstream provider. This could be an issue on the provider's end, an issue with the supplied API key or an underlying network issue causing these retries.