> For the complete documentation index, see [llms.txt](https://docs.stackai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.stackai.com/guides-and-quickstarts/evaluations-and-observability/model-usage-analytics.md).

# Model usage analytics

Model usage shows which models process requests and how many tokens they use. Review the totals, then inspect individual runs when you need to understand what contributes to usage.

{% embed url="<https://files.gitbook.com/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FSQ1Sgy933krTyK0S4JpP%2Fuploads%2FHsD6u3ItTxe5LPyhmWoR%2FG080.mp4?alt=media&token=e09faa56-95ba-4a1d-9fc8-9b08d9330e33>" %}

## Before you start

Choose the decision you need to make, such as finding which model accounts for increased usage, and use the same reporting dates for each comparison. For available allowances and limits, use [Usage, entitlements, and policy limits](https://docs.stackai.com/guides-and-quickstarts/organization-administration/usage-entitlements-and-policy-limits.md); token totals alone do not establish spend or answer quality.

## Review usage by model

Open Analytics → Models and select a reporting period.

![Analytics Models and reporting period](https://content.gitbook.com/content/SQ1Sgy933krTyK0S4JpP/blobs/CRIVruatBolYwiyyPPcR/assets/g080-g080-01-models.png)

Read provider, model, total tokens, input tokens, and output tokens together.

Select a model row to inspect its usage trends.

![Model usage trends](https://content.gitbook.com/content/SQ1Sgy933krTyK0S4JpP/blobs/EDrcL8pbmyWhUi027c4A/assets/g080-g080-02-openai.png)

Compare input and output activity within the displayed period.

Open another model's details while retaining the same date range.

![Another model in the same reporting period](https://content.gitbook.com/content/SQ1Sgy933krTyK0S4JpP/blobs/UxoZGNFlErok6ZnnZQjT/assets/g080-g080-03-compare.png)

Consistent periods make the comparison meaningful.

## Inspect tokens for a workflow run

Open a model-backed project's logs and select a relevant run.

![Run model and token usage](https://content.gitbook.com/content/SQ1Sgy933krTyK0S4JpP/blobs/MwhEQtYzWOhmDSHgw5xQ/assets/g080-g080-04-run.png)

Inspect AI Model and Used Tokens to relate aggregate activity to an individual execution.

Open the run-level token details and review the input, output, total, and model source.

![Run-level token breakdown](https://content.gitbook.com/content/SQ1Sgy933krTyK0S4JpP/blobs/40jXL0nohYfnoBkxXNqz/assets/g080-g080-05-tokens.png)

This breakdown describes the selected run rather than every execution in the reporting period.

## Consider usage alongside the response

Expand the run's Output and review the actual response.

![Output associated with the selected run](https://content.gitbook.com/content/SQ1Sgy933krTyK0S4JpP/blobs/RU9Z1t0WiIpfHEgRbCPX/assets/g080-g080-06-response.png)

Consider usage alongside the result produced rather than treating token count alone as a measure of quality.

## Important behavior

Token usage measures model processing. It does not measure response accuracy and is not a billing invoice.

Use the same date range when comparing model usage.


---

# 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.stackai.com/guides-and-quickstarts/evaluations-and-observability/model-usage-analytics.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.
