modelbenchmark.io

Kimi K2.8 Preview

Kimi · kimi-k2-8

Compare

Kimi coding model with more efficient thinking and up to 1M context, available through Kimi Code

Specification

most-agreed values

Context
1M
Max output
1M
Released
2026-09-11
Knowledge cutoff
—
Retires
—
Open weights
no
Input
text, image, video
Output
text

Price

US dollars per million tokens · most-agreed

Input
$1.00
Output
$4.00
Cache read
$0.25
Cache write
free

Available from 3 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
llmgateway$1.00$4.00$0.25—1M1M—
llmgateway-providers · tencent$1.00$4.00$0.25—1M1M—
tencent · tencent$1.00$4.00$0.25free1M1M—

Other listings of this model

same model, different key

More from Kimi

most-hosted first