> ## Documentation Index
> Fetch the complete documentation index at: https://docs.turen.io/llms.txt
> Use this file to discover all available pages before exploring further.

# LLM Activity Dashboard

> Track LLM usage and performance across your team

The LLM Activity Dashboard gives you visibility into how AI coding agents are using LLM APIs across your organization. Navigate to **Monitor > Dashboards** and select the **LLM Activity** tab. Data is shown for the last 30 days.

<Frame>
  <img src="https://mintcdn.com/turenlabsinc/T83ktNZvj9JHF81S/images/image.png?fit=max&auto=format&n=T83ktNZvj9JHF81S&q=85&s=606011a4309cb1b0198e7fe3e5ed3fa7" alt="Image" width="1587" height="765" data-path="images/image.png" />
</Frame>

## Key Metrics

The dashboard displays five summary cards at the top:

| Metric             | Description                                                                    |
| ------------------ | ------------------------------------------------------------------------------ |
| **Total Requests** | Number of LLM API calls made through Turen (click to jump to LLM events)       |
| **Avg Latency**    | Mean response time from LLM providers                                          |
| **Error Rate**     | Percentage of failed LLM API calls, with error count                           |
| **Data Volume**    | Total request and response payload sizes                                       |
| **Active Agents**  | Number of agents that sent LLM requests in the period (click to jump to fleet) |

## Provider Breakdown

A pie chart showing how usage is distributed across LLM providers:

* **Anthropic**: Claude models
* **OpenAI**: GPT models
* **Google**: Gemini models
* **Mistral**: Mistral models
* **Cohere**: Cohere models

## Model Breakdown

A horizontal bar chart showing which specific models your team is using (top 8). Model names are displayed in a friendly format (e.g., "Claude Opus 4.6", "GPT-5.2 Pro"). This helps you:

* Track adoption of newer models
* Understand usage distribution
* Identify usage patterns across your team

## Session Activity

<Frame>
  <img src="https://mintcdn.com/turenlabsinc/dfhsjfcRLggycem1/images/image-11.png?fit=max&auto=format&n=dfhsjfcRLggycem1&q=85&s=41fd74b2615db0c1677997bdb633e6cb" alt="Image" width="1608" height="762" data-path="images/image-11.png" />
</Frame>

The bottom section shows detailed session metrics:

* **Total Sessions**: Number of Claude Code sessions in the period
* **Total Messages**: Messages exchanged across all sessions, with daily average
* **Avg Duration**: Average session length
* **Unique Clients**: Number of distinct machines with sessions
* **Sessions This Week**: Daily session count bar chart
* **Activity by Hour**: 24-cell heatmap showing when your team is most active
* **Top Clients**: Ranked list of machines with the most session activity, showing hostname, session count, total bytes, and last active time