DeepSeek Unveils V4.1-Flash, Smallest Model with Native Vision

DeepSeek released V4.1-Flash, the smallest model in its new architecture family, with native vision, 552B MoE activating only 8B parameters, and 1M context, now live on Nebius.

2026-09-18 ~ 2026-09-18 · 2 related posts

• DeepSeek-V4.1-Flash lands on Nebius: 552B MoE activating 8B with 1M context — Arindam_1729 · 2026-09-18
• DeepSeek releases V4.1-Flash: smallest model in new family with native vision, $0.15/M tokens — aziz4ai · 2026-09-18