Usage rolls up everything your sessions spent. Read your own numbers at /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:
You do not have to type these yourself: give your agent the prompt 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.
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.
Also check: Sessions for the per-session detail behind these rollups, and Compare provider costs to price your real usage mix against other providers. Last modified on August 27, 2026
