美团新模型LongCat-2.0真能打，1M上下文还懂agentic coding，SWE-bench 59.5，价格也不贵。
美团LongCat-2.0是1.6T参数的MoE模型，每个token激活约48B参数，原生支持1M上下文。该模型采用LSA稀疏注意力和零计算专家架构，动态激活33B-56B参数。它设计了MOPD机制，包含Agent、Reasoning、Interaction三类专家组，按任务路由。在SWE-bench Pro上获得59.5分，与主流闭源模型相当。定价为输入缓存/输入/输出每百万tokens分别0.015/0.75/2.95美元。
The full model behind "Owl Alpha" on @OpenRouter i…
The full model behind "Owl Alpha" on @OpenRouter is here🦉 Let's meet @Meituan_LongCat 's latest flagship model, LongCat-2.0 Now Day 0 live on SiliconFlow 🔥 💰 Input Cache/Input/Output: $ 0.015/0.75/2.95 per 1M tokens ⚙️ 1.6T-param MoE (~48B active) · Native 1M context window 🧠 Built for agentic coding from the ground up: ◆ LSA: sparse attention that scales efficiently to 1M ◆ Zero-Compute Experts: dynamic 33B–56B active/token, no wasted compute ◆ MOPD: three specialized expert groups (Agent / Reasoning / Interaction), gate-routed per task 🏆 59.5 SWE-bench Pro: performance on par with mainstream close-sourced models
Start building with 🐱👇