← All models
Google · Video
Google: Gemma 4 31B
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
Open-weightIn: Image, Text, VideoOut: Text
Input / M
$0.20 / M
Output / M
$0.40 / M
Cache read / M
—
Context
262K
Released
Apr 2, 2026