Skip to content

Glossary

Prompt caching explained

Reusing a previously-sent context prefix instead of paying full input price for it again.

Why it matters for cost

Cache reads cost 0.1x the input rate; 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?
Cache reads cost 0.1x the input rate; the first write costs 1.25x (5-min) or 2x (1-hour).