AI 精选动态
智能评分 60
Kimi K2.7 Code 发布
AI 推荐理由
差异点：相比前代 K2.6，推理 token 使用量降低 30%，编码和多步工具调用能力显著提升，逼近 Claude Opus 4.8 和 GPT-5.5。核心解读
MoonshotAI 发布 Kimi K2.7 Code，32B 激活/1T 参数，编码和智能体性能提升，推理 token 使用量较 K2.6 降低 30%，接近 GPT-5.5 和 Opus 4.8，API 价格 Cache 输入 0.19、输入 0.94、输出 4.00 每 1M tokens。
全文
Better Coding with Less Overthinking
K2.7 Code takes K2.6's strong base and goes deep
Meet @MoonshotAI Kimi K2.7 Code on SiliconFlow — coding-focused, agentic, purpose-built on K2.6.
💰 Cache Input/Input/Output: 0.19/0.94/4.00 per 1M tokens
💪Improved coding & agentic performance, approaches GPT5.5 & Opus 4.8
🧠Less overthinking: 30% lower reasoning-token usage vs K2.6
⚙️Long-horizon coding: better instruction following, higher end-to-end task completion rates
32B Activated/ 1T Params | VLM | Interleaved Thinking | Multi-Step Tool Call
Try it on SiliconFlow ⬇️
https://video.twimg.com/amplify_video/2066880253092569088/vid/avc1/1920x1080/hIbwGa_R7CirWoex.mp4?tag=28
SiliconFlow (@SiliconFlowAI): Time to try K2.7 Code⬇️
https://t.co/Ck6codZr08