Gemma 4 31B (batch)
Google馃嚭馃嚫
google/gemma-4-31b-it:batchGemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.
Cost rate
0.2x
Context
262K
Released
Apr 2, 2026
Input
ImageTextVideo
Output
Text
Support
ReasoningTool callingStructured outputs
Best at
The categories where this model ranks highest.
Document analysis
#30 路 top 77%
Image understanding
#34 路 top 23%
Mathematical
#41 路 top 11%
Software & IT Services
#58 路 top 15%