DeepSeek-V4: a million-token context that agents can actually use

DeepSeek released two new MoE models, DeepSeek-V4-Pro (1.6T parameters, 49B active) and DeepSeek-V4-Flash (284B parameters, 13B active), both with a 1M-token context window.

The models are designed for efficient long-context inference and agentic tasks, featuring hybrid attention (CSA and HCA) that reduces FLOPs and KV cache memory, plus post-training improvements for multi-turn tool use.