# Google: Gemma 4 31B (batch)

Provider: google  
Category: llm  
Model ID: `google/gemma-4-31b-it:batch`

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...

## Specs

- Context length: 262144 tokens
- Max output: 235929 tokens
- Modalities: image, text, video
- Released: 2026-04-02

## Pricing

- Input: $0.39 per million tokens
- Output: $0.97 per million tokens

---
Last verified: 2026-09-04T02:00:56.012Z  
Canonical URL: https://switchy.build/directory/models/gemma-4-31b-it-batch