modelbenchmark.io

Kimi K3 Fast (Fireworks AI)

Kimi · kimi-k3-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
1M
Released
2026-07-16
Knowledge cutoff
Retires
Open weights
yes
Input
text, image, video
Output
text

Price

US dollars per million tokens · most-agreed

Input
$4.50
Output
$22.50
Cache read
$0.45
Cache write
$4.50

Available from 7 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
neuralwatt$3.00$15.00$0.301M1M
fireworks_ai$4.50$22.50$0.451M131K
fireworks-ai · accounts$4.50$22.50$0.451M131K
llmgateway$4.50$22.50$0.451M131K
llmgateway-providers$4.50$22.50$0.451M1M
pioneer · moonshotai$4.50$22.50$0.45$4.501M131K
vercel · moonshotai$4.50$22.50$0.451M131K

More from Kimi

most-hosted first