DeepSeek-V4.1-Flash reportedly offers continuous reasoning effort from 1 to 100

zainhas · x · 2026-09-10

A screenshot shared by zainhas suggests DeepSeek-V4.1-Flash supports a continuously controllable reasoning effort parameter from 1 to 100, via a reasoningeffort setting. Unlike the usual low/medium/high tiers, this would allow fine-grained trade-offs between cost and reasoning depth. Unconfirmed by official sources, but if true it marks a notable departure from discrete reasoning controls.

Related event: DeepSeek-V4.1-Flash reportedly offers continuously adjustable reasoning effort from 1 to 100(3 posts)→

Original post →

More from Models

Models channel →