DeepSeek-V4 model family

Overview

DeepSeek's flagship open-weight models: V4-Pro (1.6T total / 49B active parameters) and V4-Flash (284B / 13B active), both MIT-licensed with 1M-token context and hybrid thinking/non-thinking modes — reportedly trained on Huawei Ascend chips without Nvidia GPUs.

Released in preview on April 24, 2026 with weights on Hugging Face; the official V4 release was announced for mid-July 2026 alongside DeepSeek's first peak/off-peak API pricing, with legacy deepseek-chat and deepseek-reasoner endpoints retiring July 24, 2026.

Key Specs