Kimi K2.7 Code - Kimi’s most capable coding model yet
Kimi K2.7 Code is Moonshot AI’s latest coding-focused agentic model, built for long-horizon software engineering, 256K context, multi-step tool use, multimodal inputs, and around 30% lower reasoning-token usage than K2.6. Available in Kimi Code, Kimi API, and as open weights/code.
Replies
memi
Lower reasoning-token usage is a meaningful claim for real agent workflows. Long-horizon coding is where cost and context discipline both matter. Any benchmark examples that show where K2.7 improved most over K2.6?