Google: Gemma 4 31B

Name: Google: Gemma 4 31B
Author: OpenRouter

31B

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.

Context

262K

Max output

16K

Input price

$0.12/1M tokens

Output price

$0.37/1M tokens

Capabilities

vision

tool call

structured output

reasoning

json mode

streaming

fine tuning

batch

Details

Model IDgoogle/gemma-4-31b-it

ProviderOpenRouter

CreatorGoogle AI

Familygemma-4

License—

Parameters31B

Status—

Input modalitiesimage, text, video

Output modalitiestext

Architecture—

Knowledge cutoff—

Training data cutoff—

Release date2026-04-02

Deprecation date—

Typechat

Reasoning tokens—

Max input—

Open weight—

Sourceofficial

Last updated2026-05-14

Tools

Function Callingfunction_calling

Call external functions and APIs

Pricing

Input

$0.12

Output

$0.37

Cache write

—

Cache read

$0.02

Batch in

—

Batch out

—

Family Comparison: gemma-4

Model	Caps	Perf	Speed	Context	Max out	Pricing
Google: Gemma 4 26B A4B (free)	RVTS	—	—	262K	33K
Google: Gemma 4 31B (free)	RVTS	—	—	262K	33K
Google: Gemma 4 26B A4B	RVTS	—	—	262K	262K	$0.06$0.33
Google: Gemma 4 31B	RVTS	—	—	262K	16K	$0.12$0.37

API

GET/v1/models/openrouter/google/gemma-4-31b-it