Gemma 4 31B
google/gemma-4-31b-it
Open-weight dense model with image and video input and function calling.
MultimodalImages, Text, Video → TextReady on endue
- Open weights
- Low cost
- Images
Overview
Good for
Written by endue
- Open weights
- Low cost
- Images
Not ideal for
From the model’s specs
Nothing in the specs rules out common agent work.
Capabilities
| Tool use | Supported |
|---|---|
| Structured output | Supported |
| JSON mode | Supported |
| Reasoning | Supported |
| Vision | Supported |
| Audio input | Not supported |
| Video input | Supported |
| File input | Not supported |
| Long context | Supported |
Specifications
- Model ID
google/gemma-4-31b-it- Family
- Gemma 4
- Context window
- 262K tokens
- Input
- Images, Text, Video
- Output
- Text