Glossary · Term

reasoning token

← all terms

Definition

Plain language

Extra text a model writes to itself while working out an answer before replying.

As stated in the literature

Intermediate chain-of-thought output emitted at test time; functionally lets the model iterate over candidates and apply a rule serially, recovering much of the authoring gap.

Also called: reasoning tokens

Why it matters: These intermediate steps let a model walk through candidates one at a time instead of guessing a whole set at once, which recovers much of the accuracy it otherwise loses.

For example, before answering "which of these ten numbers are prime," the model writes out a short check for each number in turn, then gives its final list.

Heard on the show

“You get billed for reasoning tokens, so the API tells you how many the source model generated.”
Episode 238 — How a Cheap Model Reads the Flagship's Secret Reasoning Aloud

Mentioned in 4 episodes

  1. 238
    How a Cheap Model Reads the Flagship's Secret Reasoning Aloud
  2. 172
    One Bad Token Can Sink a Model's Math, And You Can Delete It
  3. 140
    When a Reasoning Model Says "Let Me Double-Check" After It's Already Decided
  4. 118
    Why the Best-Aligned AI Models Are the Easiest to Trick Into Producing Harm

Related concepts

Related terms