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

# Dashboard

> Overview of usage and costs in the selected period

<Tip>
  Home > "Admin Menu" > "Dashboard"
</Tip>

## Dashboard

The dashboard provides administrators with a central overview of usage and costs in VARIOS AI.\
At a glance, you can monitor consumption, cost trends, and usage patterns.

Use the **period selector** in the top left to set the analysis period. All metrics and charts refer to the selected period.

***

## Overview of Key Metrics

The top area displays the most important metrics as tiles:

* **Number of Requests**\
  Total number of requests in the selected period.
* **Total Costs**\
  Total costs for the selected period in USD.
* **Average per User**\
  Average costs per active user in the selected period.

***

## Chart: Overview

A line chart shows the cost trend in the selected period.\
This makes it easy to identify peak loads, trends, and unusual usage patterns.

***

## Cost Breakdown

Costs are broken down in multiple panels. Each panel has a search field and pagination.

<Warning>
  Costs are based on an extrapolation from transmitted tokens.
  Deviations from the actual costs billed by the model provider are possible.
</Warning>

| Panel                        | Description                                                                                       |
| ---------------------------- | ------------------------------------------------------------------------------------------------- |
| **Costs by User Group**      | Costs per user group. Since users can belong to multiple groups, totals may exceed overall costs. |
| **Costs by Assistant**       | Costs per assistant – shows which assistants are used most frequently.                            |
| **Costs by Chat Model**      | Costs per chat model (e.g. GPT 5.5, Claude Sonnet 4.6).                                           |
| **Costs by Embedding Model** | Costs per embedding model (e.g. text-embedding-3-small).                                          |
| **Costs by Voice Model**     | Costs per voice model (transcription and speech).                                                 |
| **Costs by Connector**       | Costs per connector (e.g. Confluence, Microsoft 365, Webhook).                                    |
| **Costs by User**            | Individual costs per user.                                                                        |
| **Costs by API key**         | Costs incurred via the API key                                                                    |

<Note>
  **User statistics** can be enabled or disabled via Admin Menu > Settings > Privacy.
</Note>

***

## Data export

Using the **"Export data"** function, all usage and cost data can be exported as a CSV file.\
This enables further processing in external controlling or reporting tools.

<Info>
  No personal data is included in the export.
</Info>

<Warning>
  **Warning**: Costs are based on an extrapolation from transmitted tokens.\
  Deviations from the actual costs billed by the model provider are possible.
</Warning>

### Included data fields

* **DateTime**: Time of the chat operation
* **Costs**: Cost of input or output in USD
* **Type**: Type of record – *input* (user input), *output* (AI response), *system* (system message such as name or summary), *api* (API call)
* **Name**: Name of the AI model used
* **Assistant**: Assistant used to execute the request
* **InputTokens**: Number of tokens processed in the user input
* **OutputTokens**: Number of tokens generated in the AI response

### Action

Click **"Export CSV"** to create the file and automatically start the download.

***

## Guide

<Steps>
  <Step title="Select period">
    Use the period selector in the top left to set the desired analysis period. All metrics and charts refer to this period.
  </Step>

  <Step title="Review overall status">
    Use the top tiles (Requests, Total Costs, Average) to get a quick status overview.
  </Step>

  <Step title="Analyze cost development">
    Use the chart to identify trends and peaks in usage.
  </Step>

  <Step title="Evaluate cost distribution">
    Use the panels to view costs by group, assistant, model, connector, or user.
  </Step>

  <Step title="Export data">
    Export the data for further analysis or for billing purposes.
  </Step>
</Steps>

***

<Tip>
  **Best practice**:

  * Check regularly (e.g., weekly) whether certain models or user groups are causing disproportionately high costs.
  * Use the cost overview by model to deliberately deploy more cost-effective alternatives (e.g., smaller models).
  * Export the data monthly for controlling and budget planning.
  * Example: Use **GPT-5 Response** only for complex tasks, while standard requests are handled with more affordable models (e.g., GPT-5 Nano).
</Tip>