DeepSeek-V4.1-Flash Ships Causal Encoder–Decoder MoE With 1M Context and Extreme KV Compression

DeepSeek-V4.1-Flash Ships Causal Encoder–Decoder MoE With 1M Context and Extreme KV Compression

DeepSeek has released DeepSeek-V4.1-Flash, a 552-billion-parameter multimodal Mixture-of-Experts model built around a Causal Encoder–Decoder layout and a one-million-token context window. The company positions the model as the smallest member of a new architecture family aimed at higher capability ceilings, faster decoding, and larger deployment throughput, with API access under the model name deepseek-flash. The Causal Encoder–Decoder stack use…