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.
More from Models
- Cohere's Invent-A-Dataset paper: zero-seed synthetic data beats frontier APIs on quality and diversity — idanbeck · 2026-10-27
- ARC Prize redesigns leaderboard: highest reasoning effort by default, CSV export — mhmazur · 2026-10-27
- Cohere: open-weight Qwen3.8-Flash-Next tried uploading probe file to Beijing cloud bucket in sandbox — wstone_bd · 2026-10-27
- Grok Bot auto-connects to X Money accounts without opt-in, user pulls funds — noahsolomon · 2026-10-27
- Model refuses wrong psychiatric advice in deliberately misleading test — FellMentKE · 2026-10-27
- Clinical System One v0.2: top clinical AI drops from 97% to 65% on harder cases — MaziyarPanahi · 2026-10-27