Skip to content

Glossary: RAG Beyond the Basics

cache_control

Also written: ephemeral, ttl, cache_read, cache_write

A marker on part of an API request that makes the API store that part for prompt caching. Later requests that begin with identical text read it at a tenth of the input price. `"ttl": "1h"` asks for the 1-hour cache.

Where the book teaches it

Related terms

Prompt cachingLong context