Skip to content

Glossary: LLMs in Production

Cache lifetime

Also written: 5-minute cache, 1-hour cache

How long a provider keeps a cached prompt. Claude offers 5 minutes or 1 hour (the 1-hour write costs 2 times input), OpenAI 30 minutes or 12 hours; pick it from the gaps in your traffic.

Where the book teaches it

Related terms

Prompt cachingCache hit rate