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

$0.2/1M tokens

Output price

$0.4/1M tokens

Capabilities

Show unsupported (4)

Reasoning & Interaction

Reasoning

Tool Calling

Output Control

Structured Output

JSON Mode

Details

Model IDgoogle/gemma-4-31b-it

ProviderOpenRouter

CreatorGoogle AI

Familygemma-4

License—

Status—

Typechat

Input modalitiesimage, text, video

Output modalitiestext

Open weight—

Parameters31B

Architecture—

Context window262K tokens

Max input—

Max output16K tokens

Reasoning tokens—

Knowledge cutoff—

Release date2026-04-02

Sourceofficial

Tools

Function Callingfunction_calling

Call external functions and APIs

Pricing

Input

$0.2

Output

$0.4

Cache write

—

Cache read

$0.05

Batch in

—

Batch out

—

Family Comparison: gemma-4

Model	Caps	Perf	Speed	Context	Max out	Pricing
Google: Gemma 4 26B A4B (free)	RTJJM	—	—	262K	33K	—
Google: Gemma 4 31B (free)	RTJJM	—	—	262K	33K	—
Google: Gemma 4 26B A4B	RTJJM	—	—	262K	236K	$0.09$0.3
Google: Gemma 4 31B	RTJJM	—	—	262K	16K	$0.2$0.4
Google: Gemma 4 31B (batch)	RTJJM	—	—	262K	236K	$0.39$0.97

API

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