Verified record · from the answer index

Google: Gemma 4 31B (free)

modeltested · static-verifiedscore 20/100signed passport ✓published 205d ago · verified 2026-10-24

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...

Declared tools (2)

image+text+video->texttool-calling

model:openrouter:google/gemma-4-31b-it:free