Model techniques map
Techniquesinference & servingreasoning control

specific method · filed under inference & serving

Always-on thinking mode

Reasoning is enabled unconditionally in generation, rather than selected or disabled per request.

Also called always-on thinking block, always has thinking enabled.

sources
2
models
2
labs adopt it
2
strongest
core

How sources treat it

One count per evidence span, weakest treatment to strongest.

core 2

Documented in

Evidence

2 spans quoted from the sources, strongest treatment first.

Kimi K3 always has thinking enabled, and will return `reasoning_content`.

coreinference servingin Kimi K3Moonshot AI

Thinking is always on — the generation prompt opens a thinking block unconditionally.

coreinference servingin GLM-5.3-FlashZ.ai

Filed alongside

Other methods under inference & serving :: reasoning control.