modelbenchmark.io

Kimi Fast Latest

Kimi · kimi-fast

Compare

Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work

Specification

most-agreed values

Context
1M
Max output
131K
Released
2026-07-27
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text, image
Output
text

Price

US dollars per million tokens · most-agreed

Input
$4.50
Output
$22.50
Cache read
$0.45

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
fireworks-ai · accounts$4.50$22.50$0.45—1M131K—

More from Kimi

most-hosted first