AI model · Google
Gemma 4 31B
Model ID: google/gemma-4-31b-it
- Input
- $0.09 per 1M tokens
- Output
- $0.34 per 1M tokens
- Context
- 262K tokens at once
- Max output
- 16K tokens per reply
- Released
- 2 Apr 2026 Google
What it can do
- YesReasoning
- YesTool calling
- YesImage input
- YesOpen weights
- NoFree to use
Takes image, text, video; gives text.
How its listing describes it
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...
Sources
- Google: Gemma 4 31B on OpenRouter — read 2 Oct 2026