Top-p Sampling
Also: nucleus sampling
A technical setting that limits which words an AI considers when writing each part of a response — only the most probable options are kept until their combined probability reaches a threshold. You rarely need to touch this. Temperature is the more intuitive control for adjusting response style. Top-p sampling is a low-level detail that developers occasionally tune when building AI applications, not something end users typically configure.
In practice
Top-p sampling is a technical setting that controls which words Claude considers when generating each part of a response. You almost never need to change it directly — temperature is the more practical control. It's a low-level parameter that developers occasionally tune when they need very specific control over output diversity in production systems.
Related concepts