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

# Usage Analytics: Token Spend Across Projects and People

> View and export AI token spend broken down by project, team member, provider, and model across any date range in ParleHub's analytics dashboard.

The ParleHub analytics dashboard gives org admins a complete, real-time picture of AI spend across every project, team member, provider, and model in the organization. Instead of reconciling line items from multiple provider invoices, you get one unified view — drillable by the dimensions that matter for professional services billing. Use it to spot high-spend engagements before they hit a budget ceiling, identify which models your team reaches for most, or pull the monthly export your finance team needs.

## Navigating to Analytics

Open **Analytics** from the main sidebar. By default, the dashboard opens at the org level, showing total spend across all projects and all members for the last 30 days.

<Note>
  Org-level analytics are visible to org admins. Project members without that role see analytics scoped to their own projects only.
</Note>

You can also reach analytics from **Org Settings → Usage & Billing → Analytics**.

## Dimensions You Can Slice By

Use the dimension tabs and filters at the top of the dashboard to break spend down along any axis — or combine multiple filters to narrow to a specific subset.

<CardGroup cols={2}>
  <Card title="Project" icon="folder-open" href="/projects/overview">
    See which client engagements are consuming the most tokens and cost. Quickly identify projects approaching their budget ceiling before enforcement triggers.
  </Card>

  <Card title="Person" icon="user-group" href="/admin/managing-members">
    See which team members are the heaviest AI users across the org. Useful for understanding adoption patterns and for reviewing individual spend against personal caps.
  </Card>

  <Card title="Provider" icon="server" href="/models/connecting-providers">
    Compare spend across Anthropic, OpenAI, Google Gemini, and Azure OpenAI. Understand where your AI budget is going at the infrastructure level.
  </Card>

  <Card title="Model" icon="microchip" href="/models/supported-models">
    Break spend down by specific model — compare `gpt-4o` vs `claude-3-5-sonnet` vs `gemini-1.5-pro`. Identify whether cost-efficient models could substitute for premium ones on lower-stakes tasks.
  </Card>
</CardGroup>

### Date Range

Set the time window using the date range picker in the top-right corner of the dashboard. Available presets:

* Last 7 days
* Last 30 days
* Last 90 days
* Custom range (pick any start and end date)

All charts and totals update instantly when you change the range. Custom ranges can span up to 12 months in a single view.

## Exporting Data

Pull a full CSV export from any analytics view to feed into your billing system, matter management platform, or financial reporting tools.

<Steps>
  <Step title="Open the Export tab">
    From the Analytics page, click the **Export** tab.
  </Step>

  <Step title="Set filters">
    Choose a date range. Optionally filter by specific projects, members, or providers to limit the export to what you need.
  </Step>

  <Step title="Download">
    Click **Download CSV**. Exports covering up to 90 days are ready immediately. Longer ranges generate a download link sent to your email within a few minutes.
  </Step>
</Steps>

Each row in the export includes:

| Column          | Description                                      |
| --------------- | ------------------------------------------------ |
| `date`          | UTC date of the usage record                     |
| `project_name`  | Project display name                             |
| `expense_code`  | Client matter or billing code set on the project |
| `person`        | Name and email of the team member                |
| `provider`      | AI provider (e.g. Anthropic, OpenAI)             |
| `model`         | Specific model name                              |
| `input_tokens`  | Tokens in the prompt                             |
| `output_tokens` | Tokens in the model response                     |
| `cost_usd`      | Total cost in US dollars                         |

<Tip>
  Export monthly and import by expense code into your practice management system to automate client AI cost recovery without manual reconciliation.
</Tip>

## One Canonical Ledger

The analytics dashboard and ParleHub's budget enforcement engine read from the same underlying token ledger. The spend number you see in a project's analytics view is the same number that triggers the 80% warning banner and the pre-flight budget block.

There is no lag, no reconciliation gap, and no difference between "reported spend" and "enforced spend." When analytics shows a project at $420 of a $500 budget, enforcement will block at \$500 — not at some independently calculated figure.

<Info>
  Token counts reflect actual billed tokens from the provider response. ParleHub does not mark up, round, or adjust token counts — what the provider reports is what you see and what you are charged for.
</Info>

<Accordion title="Why a single ledger matters for professional services">
  In a billable-hours environment, the number on your analytics export needs to match the number on any client invoice or write-off memo. Because ParleHub uses one canonical ledger for both reporting and enforcement, you can export usage data and use it directly in billing workflows — with confidence that the numbers reconcile with the limits your team experienced during the engagement.
</Accordion>