Glossary
Prompt caching explained
Reusing a previously-sent context prefix instead of paying full input price for it again.
Why it matters for cost
On most Claude models cache reads cost 0.1x the input rate (0.05x on Opus 5.5, 0.025x on Fable 5.1); the first write costs 1.25x (5-min) or 2x (1-hour).
How JP the Cat surfaces it
JP the Cat reads the real token counts behind this from the local logs on your Mac and prices them at the shipped rates — so it shows up in your actual cost, not an estimate.
Common questions
- What is prompt caching?
- Reusing a previously-sent context prefix instead of paying full input price for it again.
- How does it change what I pay?
- On most Claude models cache reads cost 0.1x the input rate (0.05x on Opus 5.5, 0.025x on Fable 5.1); the first write costs 1.25x (5-min) or 2x (1-hour).
See it in your real numbers
JP the Cat prices your actual local usage at the shipped rates — not an estimate.
Download MeowPrefer Homebrew? Install the same signed, notarized app from JP's public tap.
brew tap 8bittts/jpthecat
brew trust 8bittts/jpthecat
brew install --cask jpthecat