Skip to content

Prompt Caching, Visually Explained

Why sending the same big prompt twice can cost a tenth of the price: providers cache your prompt prefix, charge a small surcharge to write it, and discount every read that reuses it. See the break-even and how prefix stability pays.

Animated diagrams · 2 flows

Compare all 2

Sort by any column to find the right fit. Click a name to open its details.

One Prefix, Two PricesWrite prefix once → read it back cheapNoFirst call slower, then fasterProvider prefix cacheLow — one headerStable system prompts, long docs, few-shot blocks
The Break-Even CurveCumulative cost vs number of reusesNoWrite slower, reads fasterSame request, cache headerArithmetic, not plumbingDeciding whether your traffic shape profits