modelbenchmark.io

Gemma 4 12B Instruct

Google · gemma-4-12b-it

Compare

Google's Gemma 4 12B Instruct is an open-weight multimodal model for text, image, audio, and video understanding, with tool calling and structured output support.

Specification

most-agreed values

Context
262K
Max output
33K
Released
2026-08-01
Knowledge cutoff
Retires
Open weights
yes
Input
text, image, video, audio
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.05
Output
$0.25
Cache read
$0.025
Cache write
$0.25

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nano-gpt$0.05$0.25$0.025262K33K
pioneer$0.25$0.25$0.25$0.2533K33K

More from Google

most-hosted first