I Built a $5 Mac Menu Bar App That Shows LLM Token Usage in Real Time

If you're building with OpenAI, Claude, Gemini, or any LLM API, you've probably had this happen:

You debug a prompt loop. You test an agent chain. You iterate on a system prompt. Then you check your provider dashboard hours later and realize you burned way more tokens than expected.

That kept happening to me, so I built TokenBar.

What it does

TokenBar is a native macOS menu bar app that shows your LLM token usage updating in real time as you work.

• Real-time counter in your menu bar — usage updates live as API calls run
• Multi-provider — OpenAI, Claude, Gemini, Cursor, OpenRouter, Copilot, and more
• Local-first — your data stays on your machine
• Native macOS — runs on macOS 14+, sits in your menu bar, stays out of the way

Why I built this

Every token dashboard I found was either:

• An enterprise platform I didn't need
• A web dashboard I had to context-switch to
• Something that showed usage after the damage was done

I wanted a tiny, always-visible counter that catches runaway spend while it's happening.

Pricing

$5 one-time purchase. No subscription. No recurring fees.

Try it

👉 tokenbar.site

If you work with LLM APIs daily, I'd genuinely appreciate feedback on what's missing or what would make this more useful for your workflow.