TokenSpend AI
COMING SOON
Coming soon to the VS Code Marketplace. A desktop app for VS Code, verified on Windows so far.
Usage intelligence for AI coding

See what your AI coding costs, by project and by commit.

TokenSpend AI reads the usage logs your coding assistants already write and turns them into spend per project, task and commit, with budgets and forecasts. It runs on your machine. There is no account to create and nothing to send anywhere.

Meet the Creator: Jonathan Davidar (opens davidar.org in a new tab) I solve problems with creative vision and AI solutions architecture.I turn open-ended needs into designs people can use and systems teams can run. Creative strategistSolutions architectDesign thinkerUsability expertSAFe POPM practitioner
SAMPLE DATA
  • GitHub Copilot$16941%
  • Claude Code$11127%
  • Codex$5814%
  • Qwen Code$4511%
  • Continue$297%
Matched to the billEstimate
Tools read
5
Copilot, Claude Code, Qwen Code, Codex, Continue
Accounts needed
0
No sign-up and no TokenSpend AI server
Telemetry
None
Usage data stays on your machine
Trust labels
3
Estimate, GitHub meter, Matched to bill
The cockpit
The critical dials for your selected projects and period.
SAMPLE DATA
Burn vs budgetEstimate

69% of the $600 budget · 55% of the month gone

Cache health

376K of 480K input tokens from cache · Healthy

Cost per commitMeter + estimate

$412 over 145 commits

Map spend to outputs with the task timer
Start a timer on a task. AI requests made in that project while it runs are attributed to the task, so every output shows its hours next to its AI spend.
SAMPLE DATA
  1. Plan the task

    Set an hour estimate, a labor rate and whether the work is billable.

  2. Start its timer

    Work as usual. Requests in that project during the interval join the task.

  3. Stop, review, export

    Reviewed billable hours become fees. Export the timesheet as CSV or put it in the management report.

Refactor billing export00:42:17A running timer, shown in the app’s top bar.
Sample task plan with estimate, tracked time and attributed AI spend
TaskEstimateTrackedTime leftAI spend
Implement sign-in validationcheckout-service · Billable6.00h5.25h0.75h left$18.40
Refactor billing exportcheckout-service · Billable4.00h4.75hOver 0.75h$31.10
Write migration testscheckout-service · Nonbillable3.00h1.50h1.50h left$6.85
Planned13.00hTracked11.50hAI spend attributed$56.35

Attribution is by time. If two work intervals overlap, those requests stay unassigned instead of being guessed. Entries start as drafts, and only reviewed hours count toward fees. AI spend per task uses the best figure available for each request: GitHub’s bill where it is matched, then GitHub’s per-call meter, then the estimate.

For developers

Nothing to configure. It finds the logs that are already on your disk.

  • Works with the tools you useGitHub Copilot (VS Code and the Copilot CLI), Claude Code, Qwen Code, Codex and Continue. Each is labelled, and none is mistaken for another.
  • Cost where decisions get madeSpend by project, repository, task and commit, a month-end forecast, and dials for budget burn, cache health and context pressure.
  • Advice you can checkSpots light requests sent to expensive models and shows the monthly saving. It cannot judge answer quality, so you test before you switch.

For IT and finance teams

Built so you can approve it without a long review.

  • Local by designRuns on the developer’s machine. No TokenSpend AI server, no account, no telemetry. The dashboard listens on 127.0.0.1 only, and every request for your data needs a private key.
  • Metadata onlyStores the model, time, token counts, project and cost. Never prompts, replies, code or tool output. The test suite checks this.
  • Small network footprintPublic price lists are fetched with plain requests that send no data. If a developer chooses to connect GitHub billing, it uses a read-only token and talks only to api.github.com.
  • Reports you can hand overBudgets per project, executive and management reports that print to PDF, and CSV and JSON exports.
Every number says how sure it is
Spend is never presented as more certain than it is. Each figure carries one of three labels.
EstimateToken counts multiplied by published per-token rates.
GitHub meterGitHub’s own per-call charge, recorded in Copilot CLI logs, in AI credits at $0.01 each. A charge record, not an invoice.
Matched to billReconciled to GitHub’s billing data, when the developer’s account can read it.

What it does not do yet

So nobody finds out later.