DeepSeek V4.1 Flash: 552B Sparse Model with Native Vision and 1M Context

DeepSeek V4.1 Flash 1017, released October 17, 2026, is the first model built on DeepSeek’s Causal Encoder-Decoder (CED) architecture. It is a sparse mixture-of-experts model with a 552B-parameter backbone that activates 8B parameters on input and 16B on output, an asymmetric split designed to keep per-token compute low relative to total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than bolted on afterward as in the earlier experimental V4 Flash Vision model.