Reasoning Token
Noun · AI & Machine Learning
Definitions
A token used during reasoning-focused generation or internal reasoning traces, often discussed in the context of cost, latency, or long multi-step responses. The phrase emphasizes that more deliberate reasoning often consumes more tokens.
In plain English: A token consumed as part of the model's reasoning-heavy output or process.
Example: "They capped reasoning token usage in the planning workflow because the best answer was often not worth a tenfold latency increase."