← Glossary / 44 of 100
n. / Models and tokens
Temperature
Definition
Temperature is a setting that controls how random a model's output is. Low values make answers more predictable and repeatable, and high values make them more varied.
In more detail
For extraction, classification and tool calling, a low temperature is usually the safer choice. For brainstorming or creative writing, higher values help. Even at zero, outputs are not guaranteed to be identical, and some reasoning models fix the setting for you, so record it as an attribute when you compare runs.
Example
A data-extraction step runs at temperature 0 so the same invoice always gives the same fields. A name-suggestion step runs at 0.9 for variety.
Related terms
