modelbenchmark.io

Gemma 4 31B MeroMero v2 Thinking

Google · gemma-4-31b-meromero-v2

Compare

Gemma 4 31B MeroMero v2 with thinking enabled for more deliberate emotive dialogue, relationship scenes, creative writing, and multimodal roleplay.

Specification

most-agreed values

Context
262K
Max output
33K
Released
2026-07-29
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text, image
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.10
Output
$0.45
Cache read
$0.05

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nano-gpt$0.10$0.45$0.05—262K33K—
nano-gpt · thinking$0.10$0.45$0.05—262K33K—

More from Google

most-hosted first