modelbenchmark.io

Moonshot Kimi K2 Instruct

Kimi · moonshot-kimi-k2-instruct

Compare

Kimi model for long-context chat, coding, and agentic reasoning

Specification

most-agreed values

Context
131K
Max output
8K
Released
2025-01-01
Knowledge cutoff
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.574
Output
$2.294

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
alibaba-cn$0.574$2.294131K8K

More from Kimi

most-hosted first