Skip to content
JP the Cat
How it works
Widget
Privacy
FAQ
Open menu
Home
/
Library
/
Glossary
AI coding cost glossary
Plain definitions of the tokens, caching, and rate-limit terms that drive what you pay.
Prompt caching
Reusing a previously-sent context prefix instead of paying full input…
Cache read vs cache write
The difference between paying to store context (write) and paying to …
Ephemeral 5-minute vs 1-hour cache
Claude's two cache-write durations, billed at different rates — the s…
Context window
The maximum tokens a model can consider at once, including your whole…
Context cliff
The point where a request gets billed at a higher per-token tier for …
Tokenizer
How text is split into tokens — the unit you're billed on.
Notional vs real cost
Whether a dollar figure is what you actually spent or what usage woul…
List price
A provider's published per-token API rate, before any subscription or…
Used percent
How much of a rate-limit window you've consumed, as reported by the p…
Burn rate
How fast you're spending tokens or dollars over a window.
Reasoning tokens
Hidden 'thinking' tokens a model generates before its visible answer.
5-hour window
A rolling usage window that starts on your first message and caps how…
Weekly window
A 7-day usage cap that resets at a fixed time regardless of the 5-hou…
Blended $/MTok
A single effective per-million-token price across a mix of input, out…