DictionaryCaching
Minimum Cacheable Prefix
Text must be at least a certain length before it can be cached; shorter text is simply processed normally.
Definition
The smallest prompt prefix that can be cached; shorter prefixes are processed without caching. On Claude it is 512 tokens on most 5.x models, 1,024 on Opus 4.8, Sonnet 4.x, and Sonnet 5, 2,048 on Opus 4.7, and 4,096 on Opus 4.5, Opus 4.6, and Haiku 4.5.
Example
A 300-token system prompt is below the 512-token minimum on most Claude 5.x models, so cache_control on it has no effect.