Reasoning Model

Reasoning models are trained to generate an extended internal working-out before producing a final answer, and to do so without being asked. On problems with verifiable answers — mathematics, competitive programming, logical puzzles — this produces large gains over models that answer immediately.

The shift this represents is worth naming. Historically, better performance meant a bigger model trained on more data. Reasoning models improve by spending more compute at inference time instead, which is a genuinely different scaling axis and one that costs the operator on every request rather than once at training.

The tradeoff is direct: slower and more expensive per query. Many vendors now expose the effort level as a control, and the honest framing is that reasoning models are for hard problems, not all problems.

This is the axis frontier competition currently runs along, and it changes the cost model — a reasoning model can consume many times the tokens of a standard one for the same visible answer, which is invisible on a bill until you look at token counts.

Route by difficulty rather than defaulting everything to a reasoning model. Summarizing an email doesn't need it; debugging a subtle logic error does.