> For the complete documentation index, see [llms.txt](https://academy.shade.inc/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://academy.shade.inc/help-center/billing/how-do-credits-work.md).

# How do Credits work?

We introduced the credits system after our GPU cluster bill came back a few digits longer than expected. Credits allow you to continually run transcription and custom metadata jobs across your assets

{% hint style="info" %}
Enterprise customers are able to run transcription and metadata jobs for free as a part of the migration process
{% endhint %}

**The current rate for metadata is:**

* **5 credits per attribute per asset** &#x20;
* **4 credits/minute for the nano model (96% accurate, 8 languages)** &#x20;
* **8 credits/minute for the best model (99% accurate, 26+ languages)**

Credits can be purchased in bulk in different tiers from your workspace Settings/Usage page. The transcription model quality can be changed from your workspace settings.

### Example

This asset includes 3 attributes, 1 custom metadata attribute and 2 AI metadata attributes. Generating the 2 AI attributes incurred 10 credits (5 per AI attribute). Manual custom metadata attributes are free and do not incur credits. 10 credits will be used for every asset in this drive as AI metadata attributes are applied to every asset in a drive.

If an AI does not produce an output for an asset, it will not incur a credit.&#x20;

<figure><img src="https://328109618-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FlvHrZ4ybpa07fNCxAfwz%2Fuploads%2FNHYQKICivUgqQA6x1uJi%2FScreenshot%202025-02-15%20at%202.54.13%E2%80%AFPM.png?alt=media&amp;token=7cc9997e-29ff-4545-a38a-a2919ce4b52e" alt=""><figcaption></figcaption></figure>


---

# 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://academy.shade.inc/help-center/billing/how-do-credits-work.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.
