Your Claude usage limit: why it runs out, what uses it, and how to make it last

You typed one thing and the app said you hit your limit, or a long run paused partway through. This is almost always your own Claude plan's usage window, not a Booked Solid meter and not a bug. This article explains what the limit is, what actually spends it, why a big job can burn it fast, and the settings that make it last much longer.

The limit is your Claude plan's, not ours

Booked Solid runs on your own Claude subscription. Every plan (Pro, Max, and the rest) gives you a pool of usage that refills on a schedule, and Otto and Pearl draw from that same pool. We never add a separate charge or meter on top of it. So when you see "usage limit reached" or "session limit," that is Claude telling you this window is spent. It refills on its own, and you pick right back up.

What actually spends it

Everything a turn does spends usage, not just the words you type. A single request can quietly include:

• Reading your BookingHQ files, leads, and notes to ground its answer.
• Reviewing or re-checking a draft before it shows it to you.
• Tool calls (opening a page, drafting in Gmail, checking a calendar).
• Retries when something did not work the first time.

This is why asking it to review the same thing twice costs about the same as fresh work, and why one big "do everything" request can use far more than a short question. It is doing real work in the background each time.

The single biggest lever: the Thoroughness setting

The fastest way to make your usage last is to stop spending the most powerful model on small jobs.

1. Click Advanced on the right of the top bar.
2. Open the Thoroughness dropdown.
3. Pick Balanced for everyday work, or Fastest for simple tasks like tidying dictation or filing a note. Save Most thorough for the moments that truly matter: pricing, outreach, and locking in a booking.

A fresh install already starts on Balanced, so you never silently burn the most expensive option. If your usage disappears quickly, the first thing to check is that you are not sitting on Most thorough for everything. Full detail is in Most thorough, Balanced, or Fastest: what the thoroughness setting changes.

See where your usage went

The app keeps an honest record so you are never guessing. Open the Token History view to see how much each run used and where inside a long job the usage went. If one play is eating far more than the rest, that is where to trim.

When a run pauses at the limit

If a job stops partway because the window ran out, the app now says exactly that: paused at your Claude plan's usage limit. Nothing is lost. Autopilot and long jobs keep an append-only log as they work, so when your limit resets, run the same job again and it picks up from where it left off instead of starting over. (In older versions this showed only as "stopped before it could confirm it finished," which read like a fault. Update to the newest version at booked.kivimedia.co/download for the clearer message.)

Make your usage go further

• Keep Thoroughness on Balanced or Fastest for routine work; lift it to Most thorough only for high-stakes moments.
• Ask for one thing at a time rather than "do everything," so a small job cannot balloon.
• Avoid asking it to re-review work that is already correct; a repeat pass costs as much as new work.
• Keep your BookingHQ lean. When a lead is truly closed, lost, or a past one-off, archive it so future runs are not paying to re-read old history.
• Prefer the terminal (Power view) for heavy exploration if you are comfortable there; some users find it easier to watch and control the spend.

If you tune everything and still hit the wall

If you are on Claude Pro and you run heavy jobs like daily Autopilot, your plan itself may be the bottleneck. Claude Pro, about $20 a month, covers most performers, but consistently heavy use can need Claude Max, about $100 a month, which comes with a much larger usage pool. You upgrade inside your Claude account at claude.ai. Nothing changes in Booked Solid - the bigger pool simply applies the next time you run.

Still running out unusually fast?

If your usage drains far quicker than the work seems to justify even on Balanced, that is worth a look. Generate a support bundle (see Generate a support bundle and turn on support logging) and open a ticket at booked.kivimedia.co/support with your Token History screenshot. That gives us the exact picture of what a run spent so we can tell whether something is working harder than it should.