> For the complete documentation index, see [llms.txt](https://docs.euno.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.euno.ai/setup-configuration/account-settings/ai-credits.md).

# AI Credits

### Overview <a href="#toc_1" id="toc_1"></a>

AI Credits measure your account's use of Euno's AI features. Your usage appears under **AI Credits**, against your plan's allowance, in **Account Settings → Usage**. To change the allowance, contact your account manager.

### What uses AI Credits <a href="#toc_2" id="toc_2"></a>

| Activity                              | Credits                                                            |
| ------------------------------------- | ------------------------------------------------------------------ |
| **Euno Assistant** message            | 1 per message                                                      |
| **Trace Miner** processing a trace    | 1/63 of a credit for each trace that reaches question extraction   |
| **Trace Miner** canonizing a question | 1/63 of a credit for each question, the first time it is canonized |

These are free:

* Conversations that Trace Miner's sampling leaves out, and traces with nothing new since they were last processed.
* Canonizing a question again, after a re-run, a reset or a prompt update.
* Your own Context Calibration questions, which Trace Miner canonizes alongside the questions it mines.

Trace Miner charges are fractions of a credit, so usage shows two decimals, for example **12.35 AI Credits**.

### Who used them <a href="#toc_3" id="toc_3"></a>

Expand the **AI Credits** row to see usage by billing cycle and by user. Trace Miner's usage appears as two rows of its own, **Trace Miner - Trace processing** and **Trace Miner - Question canonization**, rather than under a person.

### When credits run out <a href="#toc_4" id="toc_4"></a>

Once your account reaches its AI Credits allowance, Trace Miner pauses:

* It starts no new processing batches or canonization runs.
* Processing a trace by hand, or resetting canonization, returns an error.

Mining resumes on its own once credits are available again. Trace Miner keeps raw traces for 24 hours, so traces that ended more than 24 hours earlier are not processed after a pause.

{% hint style="info" %}
Usage takes a few minutes to show up, and work already running when the allowance is reached still finishes. Trace Miner's usage can therefore go slightly past your allowance before it pauses.
{% endhint %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.euno.ai/setup-configuration/account-settings/ai-credits.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.