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...
The figures
- Made by
- Model ID
- google/gemma-4-31b-it
- Input
- $0.09 per million tokens
- Output
- $0.34 per million tokens
- Context window
- 262K tokens
- Longest answer
- 16K tokens
- Takes in
- image, text, video
- Gives back
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Reads images
- Yes
- Open weights
- Yes
- Released
- 2 Apr 2026
Read on 3 Oct 2026.