modelbenchmark.io

Kimi K2.7 Code Fast

Kimi · kimi-k2-7-code-fast

Compare

Kimi K2.7 Code with reasoning capped to a short budget for lower latency; reasoning cannot be disabled on this model

Specification

most-agreed values

Context
262K
Max output
262K
Released
2026-06-12
Knowledge cutoff
2025-01
Retires
2026-08-27
Open weights
yes
Input
text, image
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.95
Output
$4.00
Cache read
$0.095

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
neuralwatt$0.95$4.00$0.095—262K262K—
fireworks_ai$1.90$8.00$0.38—262K33K2026-08-27

More from Kimi

most-hosted first