Open Models Almanac
Methodsinference & servingreasoning control

implementation detail · filed under inference & serving

System-prompt reasoning-effort conditioning

The requested effort value is communicated to the model by adding a reasoning-effort instruction to the system prompt.

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.

sources
2
models
2
labs adopt it
2
strongest
default

Documented in

Aleph Alpha

Evidence

2 quotes from 2 sources, one card per model, each opening with its strongest.

How sources treat it
used 1default 1

Kolibri-1

Aleph Alphaadopted1 source

The chat template signals a chosen effort level to the model by adding a plain text section to the system prompt.

defaultunclearin KolibriAleph Alpha
↑