ModelWatch
← Catalog

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...

visionopen-weightslow-cost
Input price
$0.20 / 1M tokens
Output price
$0.40 / 1M tokens
Context window
262K tokens
Max output
16K tokens
Output speed
36 tokens/s
Time to first token
0.98s
Inputs
image, text, video
Open weights
Yes
OpenRouter id
google/gemma-4-31b-it
Listed
Apr 2, 2026

Benchmarks

Intelligence Index
4.4
Engineering Index
11.9

Speed and benchmarks for “Gemma 4 31B (Reasoning)” from Artificial Analysis. Prices, context window and listing date are live from OpenRouter.

Compare with others