Moonshot AI/starter

Kimi K2.7 Code

Coding-focused 1T MoE (32B active) with 256K context. +21.8% over K2.6 on Kimi Code Bench v2.

256K tokens
Context Window
starter
Minimum Plan
Moonshot AI
Provider

Best for

Agentic coding, long-horizon tasks, multi-step engineering

Strengths

Purpose-built for autonomous coding agents

30% less thinking tokens than K2.6 (more efficient)

+21.8% Kimi Code Bench v2, +31.5% MLS Bench Lite

Strong instruction following for long-horizon tasks

When to use

Choose Kimi K2.7 Code for autonomous coding workflows where the model needs to plan, execute, and iterate over many steps. It's optimized for multi-file engineering tasks and reduces unnecessary reasoning overhead.

Limitations

256K context is large but not 1M. For tasks needing broader context, M3 or Gemini may be better. Coding-focused — less versatile for general conversation.

Try Kimi K2.7 Code on Multos AI

42 models available. Switch per message. Start free.

Get Started Free