modelbenchmark.io

Kimi K2 Turbo Preview

Kimi · kimi-k2-turbo

Compare

Fast Kimi model for responsive chat, coding help, and agent loops

Specification

most-agreed values

Context
256K
Max output
8K
Released
2025-07-08
Knowledge cutoff
—
Retires
—
Open weights
no
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.15
Output
$8.00

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
abacus$0.15$8.00——256K8K—

More from Kimi

most-hosted first