> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.fabricgateway.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.fabricgateway.ai/_mcp/server.

# Review analytics

> Review traffic, errors, latency, token usage, and cost for LLM, MCP, and HTTP traffic over a time window.

**Analytics** summarizes traffic through the gateway over a time window. This topic shows you how to use the **Overview**, **LLM**, and **MCP** tabs.

## Prerequisites

Before you begin, make sure you have the following:

* A route that has received requests.
* Access to the organization that owns the route.

## View overview analytics

To view overall traffic, do the following:

1. In the sidebar, click **Admin**, and then click **Analytics**.
2. Select the **Overview** tab.
3. Select a time window: **1H**, **24H**, **7D**, or **30D**.
4. Optionally, filter by protocol with **All protocols**, **HTTP**, **MCP**, or **LLM** at the top right of the page.
5. Optionally, select **+ Namespace** to limit the data to one or more namespaces.
6. To reload the data, select the refresh icon.

The tab shows the following:

| Section                      | What it shows                                                                          |
| ---------------------------- | -------------------------------------------------------------------------------------- |
| Summary tiles                | Total requests, error rate, P95 latency, and active consumers for the selected window. |
| **Traffic**                  | A chart of requests per minute, stacked by protocol.                                   |
| **Errors**                   | A chart of client (`4xx`) and server (`5xx`) errors over time.                         |
| **P95 latency**              | A chart of the 95th percentile request duration.                                       |
| Top routes and top consumers | Tables that rank routes and consumers by traffic.                                      |

## View LLM traffic analytics

To view LLM analytics, do the following:

1. In the sidebar, click **Admin**, and then click **Analytics**.
2. Select the **LLM** tab.
3. Select a time window.

The **LLM** tab shows the following:

| Section            | What it shows                                                                                    |
| ------------------ | ------------------------------------------------------------------------------------------------ |
| Summary cards      | Total requests, total tokens, estimated cost, and error rate for the selected window.            |
| **Cost over time** | A chart of estimated spend, broken out by model.                                                 |
| **Top models**     | A table of models ranked by estimated spend.                                                     |
| **Top consumers**  | A table of consumer identities ranked by estimated spend, with requests and tokens per consumer. |

## View MCP traffic analytics

To view MCP analytics, do the following:

1. In the sidebar, click **Admin**, and then click **Analytics**.
2. Select the **MCP** tab.
3. Select a time window.

The **MCP** tab shows the following:

| Section       | What it shows                                                                                                                                    |
| ------------- | ------------------------------------------------------------------------------------------------------------------------------------------------ |
| Summary cards | Total tool calls, error rate, P95 latency, and active consumer count for the selected window.                                                    |
| Activity      | A requests-per-minute chart broken out by tools, resources, and prompts.                                                                         |
| Top tools     | A table of MCP tools (for example, `search`, `integrate`, or `execute_nrql_query`) ranked by requests, with error rate and P95 latency per tool. |
| Top consumers | A table of authenticated identities ranked by request volume, with error rate and P95 latency per consumer.                                      |

## Next steps

* To inspect a specific request behind a spike or an error, see [Inspect traces](/fabric/observability/traces).
* To reduce spend or errors, see [Route requests across models and providers](/fabric/plugins/routing).