Usage analytics: track AI coding costs and token usage

CodexUse includes a full analytics dashboard. See tokens, costs, model mix, and project breakdowns over time.

Why track usage?

AI coding assistants don't show you spending in real-time. You find out at the end of the month when the bill arrives. With multiple accounts, it's even harder to know where tokens are going.

The analytics dashboard solves this by tracking every conversation automatically:

• Token counts - Input and output tokens per session
• Cost estimates - Based on current model pricing
• Model usage - See which models consume your quota
• Project breakdown - Understand where usage clusters

What's in the dashboard

Usage summary cards

At the top, cards show key metrics for the selected time range:

• Total cost with daily average
• Total sessions with average cost per session
• Total tokens split into input and output

Usage trend chart

A line chart shows token usage and cost over time (daily view). Useful for spotting usage spikes or tracking a busy project week.

Model breakdown

A pie chart shows which models you're using most. Each slice shows token count and percentage. Helps you understand if you're using expensive models when cheaper ones would work.

Project breakdown

See top projects and usage distribution by project.

Date range filtering

Use preset filters to scope analytics:

• 7D - Past week
• 30D - Past month
• Month - Current calendar month
• All Time - Full history

All charts and summaries update when you change the range. All Time is the default.

Availability

Analytics is available on Free and Pro. Pro adds unlimited profiles and projects, live rate-limit radar, and auto-roll.

Data storage

Analytics dashboards are computed from local app and session data. CodexUse may send product telemetry to CodexUse services.

Related