DeepSeek claims V4.1-Flash beats V4-Pro, will route all V4-Pro API traffic to it from Sept 14

eyishazyer · x · 2026-09-11

DeepSeek claims its V4.1-Flash beats V4-Pro on performance, cost, speed, and total runtime — enough that all V4-Pro API traffic will be routed to Flash starting Sept 14. Per a notice relayed by TechNode, off-peak pricing for cache-hit input tokens reportedly drops to around RMB 0.02 per million tokens, though this hasn't yet appeared on DeepSeek's official pricing page.

Original post →

More from Models

Models channel →