Understanding LLM Temperature: How It Controls Token Selection

_jaydeepkarale · x · 2026-08-13

This thread explains how the temperature parameter works in LLM APIs. When predicting the next token, the model generates a probability distribution (e.g., 92% for Paris as France's capital). temperature modifies this distribution before token selection: low temperatures sharpen it, allowing high-probability tokens to dominate for predictable outputs; high temperatures flatten it, increasing the chances of selecting lower-probability tokens and adding variability.

Original post →

More from Research

Research channel →