modelbenchmark.io

K2-Think

k2-think

Compare

Kimi reasoning model for long-horizon research, planning, and tool use

Specification

most-agreed values

Context
128K
Max output
33K
Released
2025-07-26
Knowledge cutoff
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.17
Output
$0.68
Cache read
$0.085

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nano-gpt · llm360$0.17$0.68$0.085128K33K