> For the complete documentation index, see [llms.txt](https://docs.blockbrain.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.blockbrain.ai/for-admins/cost-control/monitoring-usage-and-cost.md).

# Monitoring Usage and Cost

See how many Compute Blocks are used, per user and per chat, show users what their usage costs, and export it.

#### Usage in the user profile

Users can follow their own usage in their **User Profile**. It shows as a **progress bar** with:

* the Compute Blocks used in the current timeframe
* their limit

<figure><img src="https://3232460952-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FIabFtGTeQzwfWCzp8vd6%2Fuploads%2FfafoymzNDmbwCvLAcl80%2FScreenshot%202026-08-28%20at%2015.18.36.png?alt=media&#x26;token=746229e0-e2b7-44aa-8f7f-057af886e4de" alt="" width="168"><figcaption></figcaption></figure>

***

#### Session Meter

The Session Meter shows how many Compute Blocks the current chat has used. It sits in the chat header, so users can see what a conversation costs while they work.

The meter reads, for example, **"112,253 compute blocks used"**. This is the total for the whole chat, not just the last message. In a new chat it shows a dash (-) until the first response arrives. After each response, the number updates within a few seconds.

Hover over the meter to see the details:

* **Compute blocks:** the total used in this chat.
* **Value used:** an estimated cost, for example "≈ €0.10". This only appears when an admin has turned on Show cost to users. The info icon next to it explains that the value is estimated from your organization's price and is not an invoice.
* **Details (tokens):** the tokens behind the Compute Blocks:
  * **Prompts & context:** what was sent to the model, such as your messages, instructions, and attached knowledge.
  * **AI responses:** what the model wrote back.
  * **Reused context:** context the model could reuse from earlier in the chat instead of processing it again.

<figure><img src="https://3232460952-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FIabFtGTeQzwfWCzp8vd6%2Fuploads%2Fsvv24AV1vJLiB27G5Xhg%2FScreenshot%202026-10-23%20at%2008.51.43.png?alt=media&amp;token=b24ab9c2-5cef-4584-87b0-a7fea91598aa" alt="" width="308"><figcaption></figcaption></figure>

{% hint style="info" %}
Compute Blocks follow the current price of each model. A request sent through an auto router counts at the model that answered it. See [Build Your Own Auto Router](https://docs.blockbrain.ai/for-admins/ai-models/build-your-own-auto-router.md).
{% endhint %}

***

#### Compute Block pricing

Set a price per 1 million Compute Blocks so users see an estimated cost next to their Compute Blocks in the Session Meter. A cost is easier to understand than a raw number. The price is set for your organization, so you can use the price from your own contract.

{% hint style="info" %}
Pricing works on its own. You do not need to turn on Compute Block Limits to set a price or show the cost to users.
{% endhint %}

**To set the price:**

1. Open the **Admin Panel** and go to **Compute Blocks**.
2. In the **Pricing** section, click **Edit Pricing**.
3. Enter a **Price per 1M Compute Blocks** for EUR, USD, or both. Leave a field empty to remove that price.
4. Choose the **Display currency**. This is the currency users see. The default is EUR.
5. Turn on **Show cost to users** if users should see the estimated cost in the Session Meter.
6. Click **Save**.

<figure><img src="https://3232460952-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FIabFtGTeQzwfWCzp8vd6%2Fuploads%2FGQlVSEqFRxLkwrK1GVCn%2FScreenshot%202026-10-23%20at%2011.02.38.png?alt=media&amp;token=67f31c82-d53d-4fa3-8199-092392430f70" alt=""><figcaption></figcaption></figure>

<figure><img src="https://3232460952-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FIabFtGTeQzwfWCzp8vd6%2Fuploads%2FaLyPtfU1nNQflB4mDfzb%2FScreenshot%202026-10-23%20at%2011.03.14.png?alt=media&amp;token=376dc81d-7b30-42b2-a28a-216c66aa8e25" alt="" width="375"><figcaption></figcaption></figure>

Prices must be greater than 0 and at most 10,000, with up to 4 decimal places (for example 12.5 or 0.045).

To turn on **Show cost to users**, first set a price in the display currency. Otherwise you see "Set a EUR price to show the cost to users, or pick another display currency".

**Who sees the cost**

| Show cost to users | Price set for the display currency | What users see in the Session Meter               |
| ------------------ | ---------------------------------- | ------------------------------------------------- |
| Off                | Any                                | Compute Blocks and token details only             |
| On                 | Yes                                | Compute Blocks, estimated cost, and token details |

{% hint style="info" %}
The cost shown to users is an estimate based on the price you set. It is not an invoice and can differ from your contract billing.
{% endhint %}

***

#### Usage Export

Download recorded usage as a CSV file from the **Usage Export** section of the Compute Blocks page.

1. Pick a **Date range** of up to 31 days. Export longer periods month by month.
2. Choose how rows are grouped: **None** (one row per event), **User**, **Action type**, or **Model**.
3. Optionally pick one **Action type**, or leave it on **All**.
4. Click **Export CSV**.

The per-event and per-user exports include names and emails, and any project code or cost center the user entered. You need the **Export usage events** permission.

If the export reaches the row limit, it is incomplete and you see a warning. Narrow the date range and export again.

<figure><img src="https://3232460952-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FIabFtGTeQzwfWCzp8vd6%2Fuploads%2FDGurFmWbBMw4MdocqzFM%2FScreenshot%202026-07-22%20at%2013.37.46.png?alt=media&#x26;token=73be7e66-22e9-4ca2-9c41-0e179934c1f7" alt=""><figcaption></figcaption></figure>

For dashboards of usage by bot, user, knowledge base, model and more, see Analytics.


---

# 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.blockbrain.ai/for-admins/cost-control/monitoring-usage-and-cost.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.
