Skip to content
AI HOT (Curated Pool)

Kimi K2.7 Code high-speed edition live: 5–6× faster output, 2× API price

6倍速!Kimi K2.7 Code 高速版已上线

Kimi released a high-speed variant of K2.7 Code. Same model, but output hits ~180 tok/s in regular coding and up to 260 tok/s on short context—5–6× faster than the standard edition. API price doubles; Kimi Code Plan users pay 3× token consumption. Thinking mode must be on, or it errors out or falls back to K2.6. Compared to K2.6, K2.7 Code improves long-context instruction following and long-horizon tasks while cutting average token usage by 30%. For non-coding work, K2.6 is still recommended. A three-week API top-up promo gives 20–30% vouchers on deposits of ¥500+.

Why it matters: Kimi added a fast lane to K2.7 Code that lifts output speed to 5-6x the standard version, with API prices doubled and Code Plan usage counted at 3x.

Read the original ↗Export Markdown