Menu
Customer Support & Success

AI & agents

Temperature

Also called model temperature.

In plain English

Temperature is a model setting that controls how random or predictable its answers are.

Example

With a low temperature, asking the same question twice gives nearly the same answer. With a high one, the two answers can differ a lot.

Why it matters

Anthropic's glossary describes temperature as a parameter that controls the randomness of a model's predictions while it writes text. A lower setting gives steadier, more repeatable answers. A higher setting gives more varied ones.

How it shows up on bot.ski

Botski does not run a live model on the site, so there is no temperature to set on bot.ski.

Common confusion

Temperature does not make a model smarter or more accurate. It only changes how much the wording varies.

Sources

Updated October 11, 2026.

Cookie preferences