Token Meter
Open source · Apache-2.0
See what your AI coding actually costs.
Token Meter reads your local Claude Code, Codex and Ollama logs and shows what that usage would cost at API prices — then compares it with what you actually pay. Free, open source, and everything stays on your Mac.
Version 2.0.0 · 1.7 MB · macOS 14.0 or later · Free
Universal — Apple Silicon and Intel
Signed with a Developer ID and notarized by Apple — it opens without a Gatekeeper warning.
Verify this download
Run this in Terminal after the download finishes. It prints OK if the file is byte-for-byte the one we published, and FAILED if it isn't — in which case don't open it.
cd ~/Downloads
echo "37304c3152c413b7721522d5605c9ee831b50c8c495303fa686af070dda888cc TokenMeter-2.0.0.dmg" | shasum -a 256 -cSHA-256
37304c3152c413b7721522d5605c9ee831b50c8c495303fa686af070dda888cc
Example
$1,038 of usage on a $20 plan
52× return on what you pay
An illustration, not a promise — your own number depends entirely on how much you use. And it is an estimate of API list prices, not a bill: on a subscription you pay the subscription price.
What it does
Everything in Token Meter.
Plan value
Tell it what you pay and it reframes your usage as return on the subscription, instead of a scary invoice.
Budget alerts
Set ceilings for the 5-hour block, the day, the week or the billing period. macOS notifications at 50%, 80% and 100% — each fires once per window, so a long session never spams you.
Live in the menu bar
Today's tokens, today's estimated cost, block progress or your plan multiple, visible without opening anything.
Prompt-cache analysis
In agentic coding, cache reads are usually most of the bill. See your hit rate and what caching is actually doing to the estimate.
Per-branch and per-agent costs
Break usage down by git branch, session, subagent and skill — not just by model. It answers “what did this feature cost?”
History and charts
Tokens and estimated cost over time, per model and per project, from a local database.
Export
CSV or JSON for any period, including per-event estimated cost and attribution.
Local models too
Ollama token counts and throughput, tracked separately — models running on your own Mac are free.
Also in the app: a desktop widget, a floating always-on-top readout, launch at login, and per-model pricing you can edit yourself.
Screens
See it running.
Read this first
It shows estimates, and says so.
Token Meter cannot show your real subscription quota. Anthropic and OpenAI do not publish the 5-hour or weekly limits through any API. Every number is reconstructed from log files already on your Mac and labelled estimated throughout, including the 5-hour block view.
What the cost number actually is
The cost figure is the API list-price equivalent of your tokens — what they would have cost on pay-as-you-go billing. It is not a bill, and it is not money you are owed. On a subscription you pay the subscription price, whatever this number says.
Claude Code logs
~/.claude/projects/**/*.jsonl
EstimatedParsed on your machine, no network. The logs are known to under-report token counts, sometimes significantly.
Codex CLI logs
~/.codex/sessions
EstimatedParsed on your machine, no network. Same under-reporting caveat as Claude Code.
Ollama (local models)
127.0.0.1
MeasuredReal token counts from the local endpoint — and no cost to estimate, because the model runs on your Mac.
Usage from the Claude or ChatGPT web and desktop apps leaves no local trace, so it is invisible to this tool. The 5-hour block is Claude Code only, so Codex usage never inflates it. Billing-grade connectors to the provider usage APIs are planned, not shipped.
Install
Two ways to run it.
Take the notarized build, or build it yourself from source. Both end up in the same place.
Download and drag
Open the disk image and drag Token Meter into your Applications folder. That's the whole install — the build is signed with a Developer ID and notarized by Apple, so it opens straight away.
Grant Full Disk Access
The CLI logs live under your home folder and macOS gates access to them, so reading them needs Full Disk Access in System Settings → Privacy & Security. The app detects the missing permission and walks you through granting it.
Or build from source
Needs macOS 14 and Xcode 16 or later. A source build is signed ad-hoc, which is fine locally — macOS may just re-confirm file access between launches.
git clone https://github.com/unichat-dev/token-meter.git
cd token-meter
make bootstrap
make buildLatest release
TokenMeter-2.0.0.dmg
macOS · Universal — Apple Silicon and Intel
- Version
- 2.0.0
- Size
- 1.7 MB
- Requires
- macOS 14.0 or later
- Released
- Aug 17, 2026
Signed and notarized by Apple
Verify what you downloaded
Run this in Terminal after the download finishes. It prints OK if the file is byte-for-byte the one we published, and FAILED if it isn't — in which case don't open it.
cd ~/Downloads
echo "37304c3152c413b7721522d5605c9ee831b50c8c495303fa686af070dda888cc TokenMeter-2.0.0.dmg" | shasum -a 256 -cSHA-256
37304c3152c413b7721522d5605c9ee831b50c8c495303fa686af070dda888cc
The same build is served from both places, so this digest matches either copy.
GitHub is the canonical copy — the link above — so downloads are counted in one place. This mirror is the identical build, for when GitHub isn't reachable.
What's new
New in Token Meter 2.0.0.
Version 2.0 answers a question 1.x couldn't: whether the subscription is worth it.
- NewPlan value — your usage shown as return on what you pay.
- NewBudget alerts at 50%, 80% and 100%, delivered as macOS notifications.
- NewPrompt-cache hit rate, and what caching does to the estimate.
- NewCost broken down by git branch, session, subagent and skill.
- NewCSV and JSON export for any period.
- NewA live readout in the menu bar.
- NewLaunch at login, and in-app update checks.
- FixedMore accurate cost — 1-hour cache writes and server-side web search are now billed correctly.
- ImprovedMuch faster: a warm start on a large log archive went from around 34 seconds to around 2.
- ImprovedSettings reorganised into a sidebar.
Privacy
Nothing leaves your Mac.
Log parsing is on-device, history lives in a local database, and nothing about your usage is ever transmitted. No account, no telemetry, no analytics.
All of it stays local
Parsing happens on-device and history lives in a local database under ~/Library/Application Support/TokenMeter.
Three network calls, all yours
A daily model-pricing refresh, an update check against GitHub, and your own local Ollama endpoint if you use it. Nothing about your usage travels with any of them.
Why it asks for Full Disk Access
Claude Code and Codex write their logs under your home folder, and macOS gates that whole area behind Full Disk Access. It is the only way to read them — the app reads those log files and nothing else.
No keys, no telemetry
This release holds no API keys at all. When connectors land, keys will live in the macOS Keychain only — never the database, defaults, or logs.
Source
Read it, fork it, ship it.
The whole thing is on GitHub under Apache-2.0. Issues and pull requests are welcome — students on our teams review them alongside everyone else.
github.com/unichat-dev/token-meter
Build with us
Want to build the next one?
Open an issue, send a pull request, or join the studio and ship something of your own — with your name on the commits.