DeepSeek-V4 shipped two models with 1M-token context in April 2026

DeepSeek’s API documentation announced the DeepSeek-V4 preview on April 24, 2026, shipping two models: DeepSeek-V4-Pro (1.6T total / 49B active parameters) and DeepSeek-V4-Flash (284B total / 13B active parameters), both with a 1M-token context window and open weights on Hugging Face.

Sources

Last verified June 6, 2026