DeepSeek launches V4 Preview with two models: V4-Pro (1.6T total/49B active) and V4-Flash (284B/13B active), both open-sourced with 1M context length. Performance rivals top closed-source models, with structural innovations like DSA attention. API available now, older models retire July 2026.
原文翻译:DeepSeek发布V4预览版,包含两个模型:V4-Pro(总参数量1.6T/激活参数49B)和V4-Flash(总参数量284B/激活参数13B),均开源并支持100万上下文长度。性能媲美顶级闭源模型,具有DSA注意力等结构创新。API现已可用,旧模型将于2026年7月退役。
DeepSeek-V4 is a preview of the next-generation large language model with 1M context, leading open-source performance in knowledge, reasoning, and agent capabilities. It comes in Pro and Flash versions, both open-sourced with dual reasoning modes.
原文翻译:
DeepSeek-V4是新一代大语言模型预览版,拥有百万上下文,在知识、推理和Agent能力方面达到开源领先水平。提供Pro和Flash两个版本,均已开源并支持双模式推理。
[Original Summary]
DeepSeek officially released the preview version of DeepSeek-V4, supporting 1M token context, open-sourcing the model, and offering two versions (Pro & Flash) with enhanced Agent capabilities, marking a milestone for open-source models to rival top closed-source models.
原文翻译:
DeepSeek正式发布DeepSeek-V4预览版,支持百万token上下文,开源模型,提供Pro与Flash两个版本,并增强Agent能力,标志着开源模型首次比肩顶级闭源模型。
DeepSeek-V4 preview version is officially launched and open-sourced, featuring 1M ultra-long context, enhanced Agent capability, world knowledge, and reasoning performance. Two versions: Pro and Flash. API updated, open-source links provided.
原文翻译:DeepSeek-V4 预览版正式上线并开源,拥有百万字超长上下文,Agent能力、世界知识和推理性能均领先。提供Pro和Flash两个版本,API已更新,开源链接已发布。
WeChat has begun testing an AI-powered search feature integrating the DeepSeek-R1 model, offering a more diverse and intelligent search experience. The feature is currently in limited testing, pulling data from public WeChat official accounts and other online content, without using private user data.
原文翻译:微信已开始测试集成DeepSeek-R1模型的AI搜索功能,提供更丰富、更智能的搜索体验。该功能目前处于有限测试阶段,从微信公众号和公开网络内容中提取数据,不使用用户隐私数据。
The article analyzes the market shock caused by DeepSeek's competitive AI models, questioning the necessity of massive GPU infrastructure investments. It highlights DeepSeek's cost-efficient training methods, the potential shift towards more efficient AI scaling, and the implications for Nvidia and datacenter investors. Experts suggest that while DeepSeek's innovations are significant, they will not drastically reduce AI infrastructure demand but will encourage more efficient resource utilization.
原文翻译:
本文分析了DeepSeek竞争性AI模型引发的市场冲击,质疑大规模GPU基础设施投资的必要性。文章强调了DeepSeek的成本高效训练方法、向更高效AI扩展的潜在转变,以及对英伟达和数据中心投资者的影响。专家认为,虽然DeepSeek的创新意义重大,但不会大幅降低AI基础设施需求,而是会鼓励更高效的资源利用。
This article provides a comprehensive guide on DeepSeek SEO and AI GEO optimization, covering 16 steps for AI reasoning optimization, 15 steps for GEO optimization, prompt types, and keyword strategies to improve brand ranking in AI search.
原文翻译:本文提供了DeepSeek SEO和AI GEO优化的全面指南,涵盖AI推理优化的16个步骤、GEO优化的15个步骤、提示词类型和关键词策略,以提升品牌在AI搜索中的排名。