Abokado Labs · Model Meter

How much of your AI budget is actually left?

Model Meter is a small macOS menu bar app for people who lean on Codex and Claude all day. It shows how much of your 5-hour and weekly limits you've used — and how much you have left — without ever opening Codex or Claude.

Download for macOS → How it works

Free & open source MIT-licensed. Source on GitHub.

The whole UI, most of the time

It lives here.

A single line in your menu bar, next to the clock. Glance at it between prompts — no app to switch to, no dashboard to load, no tab to keep alive.

Model Meter showing 11% Codex used and 4% Claude used in the macOS menu bar.
Codex 11% · Claude 4% — your actual menu bar, not a mockup.
How it works

A quiet readout. One click for the rest.

Model Meter sits in your menu bar showing a single line like C 74% · Cl 98%. Click it and a small popover drops down with the full breakdown — used, available, time elapsed in the current period, next reset. Click anywhere else and it tucks itself away.

Glanceable by design
One click. Every stat you need. The popover shows your 5-hour rolling usage and your weekly allowance for both Codex and Claude, rendered identically so the numbers compare at a glance. Click anywhere else and it dismisses — you're back where you were.
Local-first for Codex
Reads ~/.codex directly. No OpenAI API call, no third-party balance service. Model Meter surfaces the rate-limit snapshots Codex already writes locally on your machine.
Authenticated for Claude
Signs in with your Claude account. Session credentials live in macOS Keychain — never in a config file, never on a server we run. Disable Claude entirely if you only use Codex.
No telemetry
The app phones home for one thing: update checks. Nothing about your usage, your account, or your activity is sent anywhere. The Sparkle update check pulls a small XML file from this site and that's it.
When you click

The full breakdown, two providers at a time.

One click drops down a popover with everything worth knowing about the current period. Used percentage, available percentage, a progress bar, and a small marker showing how far through the reset period you are. If the bar's ahead of the marker, you're using that provider faster than the period's pace.

  • 5-hour rolling on the left — your short session limit.
  • Weekly allowance on the right — your longer billing-cycle limit.
  • Plan and account state below — including next reset time.
  • Pace marker in white — elapsed time in the period, so usage has context.
Model Meter popover open, showing Codex and Claude usage with 5-hour and weekly periods for each.
Model Meter settings panel showing menu bar configuration options.
Make it yours

Show only what you care about.

Toggle Codex or Claude independently. Pick which percentage shows in the bar — 5-hour used, 5-hour available, weekly used, or weekly available. Switch provider labels between letters (C / Cl) and icons. Three font sizes for crowded menu bars.

  • Letters or icons — your call.
  • Optional "warn when ahead of pace" turns the value red when you're burning faster than the period's pace.
  • A live preview shows exactly what your menu bar will look like before you commit.
Download

Latest build.

Model Meter 1.0.0 is live — free to download, free to use, free to fork. Signed and notarized by Apple, delivered directly. Future updates arrive automatically through Sparkle — no reinstall, no App Store.
Download Model Meter 1.0.0 → View appcast

Requires macOS 14 or later. Apple Silicon and Intel Macs supported. Signed and notarized with an Apple Developer ID.

Open source

Free, MIT‑licensed, contributions welcome.

The source lives on GitHub. Read it, fork it, file an issue when something breaks, or open a pull request when you want the next version to do something it doesn't yet. The contributing guide covers setup, scope, and how PRs land.

View source on GitHub → Contributing guide Report an issue
It's the tiny readout you keep glancing at — not another dashboard to open.
FAQ

Reasonable questions.

Does Model Meter use my OpenAI API key?

No. Codex data is read locally from ~/.codex — the same folder the Codex CLI writes to on your machine. There's no OpenAI API call involved and no billing implication.

How does Claude usage get read?

With your permission, Model Meter signs in to Claude through a small in-app web view and stores the resulting session in macOS Keychain. It then calls Claude's authenticated usage endpoint — the same one the Claude website uses to show you your own usage. If Claude ever changes that behavior, the integration may need to be refreshed.

Does it use my Anthropic API key?

No. Model Meter reads usage of your Claude.ai plan, not API consumption. The two are billed separately by Anthropic and the API has its own console.

Why isn't it on the Mac App Store?

Model Meter reads files in ~/.codex and uses a WebKit window for Claude sign-in. Both are at odds with the App Store sandbox in ways that would gut the app. So it's distributed directly, signed and notarized by Apple, with Sparkle handling updates.

Is there an iPhone version?

No. The Codex data lives on the machine where you run Codex, which is a Mac. An iPhone version wouldn't have anything to read.

Not affiliated with OpenAI, Anthropic, Claude, ChatGPT, Codex, or Apple. Codex, Claude, and their respective marks belong to their owners. · Privacy · Feedback