DeepSeek-V4
The efficiency school scales up: 1.6T parameters, MIT license, 1M context.
您正在查看一条 AI 模型记录：谁构建了它、它能做什么，以及其背后的硬件与数据。
DeepSeek-V4 went live in preview on April 24, 2026 in Pro and Flash variants with API access and open weights under MIT. V4 Pro is a 1.6-trillion-parameter mixture-of-experts activating 49B per token, pairing MoE with sparse attention for a 1M-token context — and posting 80.6% on SWE-bench Verified (as reported in launch coverage), frontier-class coding from an open model. It extends the V3/R1 lineage's argument that engineering efficiency, not raw compute access, sets the pace under export controls.
规格与关键参数
每个数据均标注来源依据：厂商规格、厂商声明、公开报道、估算或官方数据。"未公开披露"即字面含义——我们从不捏造数值。
Overview
它如何与整个技术栈相连
本记录的关联链接一览——点击分组可直接跳转。
开发方
测试平台
基于
前代产品
来源
Open-source LLM landscape 2026 (V4 details) ↗ · DeepSeek ↗
记录审阅截至 2026-08-31 — 查看 方法论.