做智能体应用的开发者可以立即在 LangChain 中调用 Nemotron 3 Ultra，推理快 5 倍、成本降 30%，值得直接上手试。
LangChain 宣布原生支持 NVIDIA 最新发布的 Nemotron 3 Ultra 模型，并在发布当天即提供对 Deep Agents 的支持。Nemotron 3 Ultra 是一个 550B 参数的 MoE 架构开放模型，专为长时间运行的智能体任务设计，推理速度提升 5 倍，复杂智能体任务成本降低 30%。作为 Nemotron Coalition 成员，LangChain 将与 NVIDIA 合作，推动开放模型的共享与构建。这一集成让开发者能立即在 LangChain 生态中使用该模型构建高性能智能体应用。
LangChain supports @NVIDIA Nemotron 3 Ultra out of the box, with Day 0 support for Deep Agents. As ...
LangChain supports @NVIDIA Nemotron 3 Ultra out of the box, with Day 0 support for Deep Agents. As a member of the Nemotron Coalition, we are excited to work with NVIDIA to make it even easier and more accessible to share and build on top of open models. NVIDIA AI @NVIDIAAI Today we're shipping Nemotron 3 Ultra. A 550B MoE frontier-intelligence open model built for long-running agents. It delivers 5x faster inference and lowers the cost of complex agentic tasks by up to 30% versus other open frontier models. Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 5 🔄 3 ❤️ 14 👀 1382 📊 5 ⚡