All terms

Temperature

A sampling parameter that controls how random or focused an LLM's next-token choices are.

Large Language Models1 min read

Definition

Temperature scales the probability distribution before sampling. Low values (near 0) make outputs more deterministic; higher values increase diversity and surprise.

It does not make the model "smarter" — it changes how boldly it samples from what it already believes.

In simple terms

Low temperature is carefully picking the safest menu item. High temperature is trying the chef's weird specials — more variety, more risk.

Where you see it

  • Customer support bots use low temperature for consistent answers.
  • Creative writing uses higher temperature for varied prose.

How it works

  1. 1.Model scores tokens

    Logits for each vocabulary item.

  2. 2.Divide by temperature

    Higher T flattens the distribution.

  3. 3.Sample

    Draw the next token from the adjusted probabilities.

Why it matters

  • Temperature is one of the first knobs product teams tune for reliability vs creativity.

Often confused

  • Temperature 0 guarantees factual correctness.

    It reduces randomness but the model can still confidently produce false content.