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
More from Google
most-hosted first