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.
More from Models
- Kimi K3.1 Pro tops MathArena open models, closing frontier gap to about 6 months — teortaxesTex · 2026-10-26
- Ruff creator Charlie Marsh: frontier models find infinite bugs in any software — charliermarsh · 2026-10-26
- Dev testing one skill across Opus 5.5 and Sol 6.1 finds instruction following 'all over the map' — lucasmeijer · 2026-10-26
- supermemory unveils learner-1, claiming continual learning for any model — julianweisser · 2026-10-26
- Anthropic says Opus 5.5 cuts cost per task by ~40% vs Opus 5 — taufiqintech · 2026-10-26
- AI search APIs ranked: top 12 within 7 points, yet prices differ nearly 7x — FinanceYF5 · 2026-10-26