Open Models Almanac
Methodsinference & servingreasoning control

single mention · inference & serving

Per-request thinking control

A request can independently configure whether or how much the model thinks.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See reasoning control for the methods filed beside it.

Also called per-request control via enable_thinking.

Filed under inference & serving › reasoning control