Model techniques map
Techniquesinference & servingreasoning control

specific method · filed under inference & serving

Thinking mode selection

Thinking can be toggled on or off for a request, or models may support distinct thinking and non-thinking modes.

Also called Thinking mode, thinking, Thinking/Non-Thinking modes, dual modes (Thinking / Non-Thinking).

sources
4
models
4
labs adopt it
3
strongest
default

How sources treat it

One count per evidence span, weakest treatment to strongest.

optional 3default 1

Documented in

Further reading

Picked by hand, not extracted: where to read more, not evidence for anything on this page.

Evidence

4 spans quoted from the sources, strongest treatment first.

Qwen3.6 models operate in thinking mode by default, generating thinking content signified by thinking ... response before producing the final responses.

defaultinference servingin Qwen3.6-35B-A3BQwen

M3 supports toggling thinking on or off. With thinking enabled, the model is suited to complex reasoning, agentic tasks, and long-horizon collaboration; with it disabled, it responds faster

optionalinference servingin MiniMax-M3MiniMax

A thinking mode can be toggled on or off per request.

optionalinference servingin M3 APIMiniMax

Both models support 1M context & dual modes (Thinking / Non-Thinking)

optionalinference servingin DeepSeek-V4DeepSeek

Filed alongside

Other methods under inference & serving :: reasoning control.