modelbenchmark.io

gemma 4 31B turbo TEE

Google · gemma-4-31b-turbo-tee

Compare

Largest Gemma 4 instruction model for open, self-hosted chat and reasoning

Specification

most-agreed values

Context
131K
Max output
66K
Released
2026-04-02
Knowledge cutoff
Retires
Open weights
yes
Input
text, image
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.12
Output
$0.37
Cache read
$0.012

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
chutes$0.12$0.37$0.012131K66K

More from Google

most-hosted first