Last month I spent $340 on Claude API calls. I only realized when the invoice hit. Sound familiar?
The problem is not the spending. It is the zero visibility while you work. You fire off prompts, switch between models, debug for an hour, and by the time you check the dashboard the damage is done.
I started using TokenBar, a macOS menu bar app that shows your token usage and cost in real time as you work. Think of it like a gas gauge for your AI spend.
What it shows:
- Live token count per session
- Cost per model
- Which conversation is burning the most
- Running daily and weekly totals
What changed for me:
- I caught runaway loops. A debugging session was burning $15 in 20 minutes. I saw the counter climbing and killed it. Without the counter I would have let it run much longer.
- I switched models intentionally. When you can see expensive models costing much more per prompt, you start asking whether the task really needs them. Often it does not.
- I cut monthly spend by 40 percent. Just from being aware. No code changes, no workflow changes. Just visibility.
Price is $5 lifetime. It is macOS native, no subscription, and built for people who work in AI all day.
If you are paying per token daily, install it before your next prompt sprint and watch where the spend leaks.
Top comments (0)