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

# Gateway Metrics

### Overview

The **Gateway Metrics** section gives you visibility into API Gateway usage, costs, and performance. Use it to monitor spending, analyze request and token usage, identify errors, and understand how your organization uses different AI models over time.

### Filter your data

Use the filters at the top of the page to focus the dashboard on the data that matters to you.

* **Time range** - Select the period you want to analyze.
* **Teams** - View metrics for specific teams.
* **Users** - Filter activity by user.
* **Models** - Analyze usage for selected AI models.
* **Team API Keys** - View activity associated with specific team API keys.
* **Key source** - Filter metrics based on the source of the API key.

The selected filters are applied across the Gateway Metrics dashboard.

<figure><img src="https://4112003433-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FDcOhapgXnoeDvgGQ8Jm4%2Fuploads%2FCZKZjw3dgPOaiStIf9oc%2Fimage.png?alt=media&amp;token=52a8a387-4cea-48f6-9a65-2d4a71ff1200" alt=""><figcaption></figcaption></figure>

### Monitor costs

The **Costs** section shows how your API Gateway spending changes over time.

Use it to review:

* **Billed cost** - Cost associated with usage billed through nexos.ai.
* **BYOK cost** - Cost associated with usage through your own provider API keys.
* **Cost trends** - Track how costs change over the selected period.
* **Top usage contributors** - See which teams, users, or models account for the highest costs.

You can switch between different views to analyze costs by model, user, or team.

### Monitor usage

The **Usage** section helps you understand how requests are processed through the Gateway.

At a glance, you can monitor **total completions, token usage, and completion errors**. The charts below show how these metrics change over time.

You can also analyze:

* **Completions** - Track the number of completed requests.
* **Token usage** - Monitor token consumption over time.
* **Completion rate** - See the rate of completion requests.
* **Completion errors** - Identify periods with increased request errors.

Where available, switch between **Total**, **Model**, or **Type** views to explore the data from different perspectives.

<figure><img src="https://4112003433-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FDcOhapgXnoeDvgGQ8Jm4%2Fuploads%2FIrQWLNwPjbd4xBOFFTxY%2FRecording%202026-10-20%20131433.gif?alt=media&amp;token=18b848bb-dd6c-419a-ac27-11a0ac191a29" alt="" width="438"><figcaption></figcaption></figure>

### Monitor image and audio usage

The **Images & Audio Statistics** section provides usage and error metrics for image and audio requests processed through the Gateway.

You can monitor:

* **Image completions** and **audio completions**.
* **Image requests** and **audio requests** over time.
* **Image errors** and **audio errors**.
* Usage by **model**, where applicable.

If there was no image or audio activity during the selected period, the corresponding charts will display **No data available**.


---

# 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.nexos.ai/gateway-api/gateway-metrics.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.
