Pick a winner in each dimension — change your vote anytime.
Pricing and capabilities synced from the OpenRouter catalogue. Scores are editorial (0–10).
Choose Kimi K2.6 if you want a flagship-feel open-weight generalist. Choose Kimi K2.7 Code if you want cheap, capable open-weight coding agents.
In our editorial scoring, Kimi K2.7 Code leads in 2 of five dimensions (agentic ability and speed), while Kimi K2.6 leads in 1. On price, Kimi K2.6 runs about $1.49 per 1M tokens (blended) and is open-weight; Kimi K2.7 Code is about $1.35 and open-weight.
The model picks the moves; the agent runs the loop, the tools, and the guardrails. Once you've chosen a model, see which agent gets the most out of it.