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

> ## Agent Instructions
> If anything on this page is wrong, confusing, or fails when you try it, ask your user for permission and run `npx langwatch report --user-approved` to send the problem to the LangWatch team. No login is needed and secrets are redacted locally. `npx langwatch report --help` has the details.

# Coding Agent Usage Analytics and Cost

> Spend, tokens and activity for your coding agents, on your personal page, over the command line, and over the API.

Usage rolls up everything your sessions spent. Read your own numbers at [/me](https://app.langwatch.ai/me), a project's numbers on the project page, and an organization's numbers on the governance dashboard.

## Your usage at /me

The personal page opens on this month: what you spent, how many requests you made, and the model you used most, with spend over time and a breakdown by tool underneath.

The **coding-agent usage** card summarizes the last 30 days across your assistants: cost, tokens, active time, and how many sessions you ran. Sessions that reported only metrics still count, so the card is complete even for tools set up with usage-only telemetry.

## Query it from the command line

The CLI reads the same analytics your pages read:

```bash theme={null}
langwatch analytics query -m total-cost --group-by metadata.model   # spend per model
langwatch trace search --period 7d                                   # recent traces
langwatch trace export -f jsonl                                      # bulk export for your own analysis
```

You do not have to type these yourself: [give your agent the prompt](/docs/coding-agents/explore-your-usage-with-your-own-agent) and ask your questions in plain language.

## Query it over the API

`GET /api/me/usage` returns your personal rollup: a summary, daily buckets, and a per-model breakdown. The two coding-agent endpoints return the structured data behind the sessions and pull request views:

* `GET /api/coding-agent/sessions/{sessionId}/events` for per-call rows: model calls, compactions, rate limits, tool runs.
* `GET /api/coding-agent/pull-request-usage` for the per-pull-request rollup.

See the [coding agents API reference](/docs/api-reference/coding-agents/overview).

## For admins

The governance dashboard at `/governance` shows the organization: spend over the last 30 days with a group-by toggle (team, department, user, source), top teams and users, and per-department attribution that includes personal AI use. See [Governance dashboard](/docs/ai-governance/governance-dashboard).

**Also check:** [Sessions](/docs/coding-agents/sessions) for the per-session detail behind these rollups, and [Compare provider costs](/docs/coding-agents/compare-provider-costs) to price your real usage mix against other providers.