← Glossary / 46 of 100
n. / Models and tokens
Reasoning model
Definition
A reasoning model is a language model that spends extra tokens thinking through a problem before it gives an answer. It tends to do better on multi-step tasks, at the price of more latency and cost.
In more detail
The thinking tokens are billed as output tokens even when the provider hides the text. That makes usage numbers in traces important: a short visible answer can hide a large bill. Many providers let you set how much effort the model spends, so you can use a lower setting for simple steps and a higher one for hard ones.
Example
The same question costs 150 output tokens on a standard model and 2,400 on a reasoning model, because most of those tokens are internal reasoning.
