> For the complete documentation index, see [llms.txt](https://docs.console.zenlayer.com/welcome/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.console.zenlayer.com/welcome/ai-gateway/ai-gateway-usage-analytics.md).

# AI Gateway Usage Analytics

Usage Analytics provides visibility into how your AI Gateway is being used, helping you understand consumption patterns, model adoption, and overall usage trends.

<div align="left" data-with-frame="true"><figure><img src="https://3201622183-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F9X3FDdkCL2HzhbPpPMFt%2Fuploads%2Fgit-blob-5ce81753b4d82ebcd7404c759fe4734b051baa39%2Fai%20gateway%20analysis.png?alt=media" alt=""><figcaption></figcaption></figure></div>

### Available Metrics

The following metrics are available to help you analyze usage at the model level:

* **Token usage by model**\
  Displays the total number of tokens consumed by each model over the selected time range.
* **Request count by model**\
  Shows how many API requests were sent to each model, helping identify traffic distribution.
* **Input tokens**\
  Represents tokens consumed by request inputs, useful for understanding prompt size and request complexity.
* **Output tokens**\
  Represents tokens generated by model responses, useful for evaluating response length and cost impact.

You can select specified AI gateway and filter data by time range (e.g., last 6 hours or custom intervals).

{% hint style="info" %} <mark style="color:blue;">**Note**</mark>

* <mark style="color:blue;">Only models that report input and output token usage are included in analytics.</mark>
* <mark style="color:blue;">Usage data may be delayed by several minutes and may not appear in real time.</mark>
  {% endhint %}
