modelbenchmark.io

Kimi K2 0711 Fast

Kimi · kimi-k2-instruct-fast

Compare

Compact GPT model for low-latency assistance and high-volume workloads

Specification

most-agreed values

Context
131K
Max output
16K
Released
2025-12-15
Knowledge cutoff
Retires
Open weights
yes
Input
text, pdf
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.40
Output
$1.80
Cache read
$0.20

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nano-gpt$0.40$1.80$0.20131K16K

More from Kimi

most-hosted first