Enterprise DNA
L Models Best vision

Gemma 4 31B

by Google

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

Visit Google Submit your build →
G4

Models

Gemma 4 31B

Added 10 July 2026

#google

Overview

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...

How to use / API access

Call via OpenRouter with model id `google/gemma-4-31b-it`.

  • openrouter · google/gemma-4-31b-it Docs

OpenRouter id: google/gemma-4-31b-it

Benchmarks

  • Intelligence Index (artificial-analysis) : 29.4 index
  • Coding Index (artificial-analysis) : 43.4 index
  • Agentic Index (artificial-analysis) : 14.4 index

Notes

Gemma 4 31B is listed in the EDNA Models directory from the OpenRouter catalogue.

← Back to Models Submit your own entry →