Does Gemma 4 31B support zero data retention?

Yes. Gemma 4 31B is available with zero data retention by default on Gemini, Geodd through the Opper gateway.

Where is Gemma 4 31B hosted?

Gemma 4 31B runs on US hosting routes through the Opper gateway.

Is Gemma 4 31B trained on prompts and outputs?

No. Every hosting route for Gemma 4 31B is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Gemma 4 31B?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Gemma 4 31B. Contact hello@opper.ai to receive it.

Gemma 4 31B

by Google

Gemma 4 31B is the dense flagship of the Gemma 4 family, with 31 billion parameters and nearly all of them active during inference for maximum output quality. Developed by Google DeepMind on the same research lineage as Gemini 3, it targets complex reasoning and agentic workflows and accepts text, image, and video inputs. It carries a 256K token context window, native function calling, structured output, configurable thinking modes, and comprehension across more than 140 languages. A hybrid attention design interleaves local sliding-window attention with full global attention, allowing efficient processing of long documents without losing context. Ranked #3 among open models on the Arena AI text leaderboard, Gemma 4 31B pairs frontier-level results with an open-weight Apache 2.0 release suitable for fine-tuning and deployment.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

256K

Max output

Input price

— /1M

Output price

— /1M

US residency available
Zero data retention on pay-as-you-go
No training by default
GDPR DPA available

Available routes

Gemma 4 31B runs on 2 different routes through the Opper gateway. Compare residency, ZDR, and training posture at a glance — full data-handling detail per route below.

Provider	Region	Zero data retention	Training	Input	Output
Gemini	US	Enterprise	No	—	—
Geodd	US	Zero data retention	No	$0.13	$0.37

Training posture across routes: No training on prompts by default.

Data handling per route

Each route hosting Gemma 4 31B has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Gemini — United States🇺🇸

Zero data retention is available via Opper Enterprise contract. No training on customer data. US; SCCs; DPA available.

Zero data retention: Available via Opper Enterprise contract.
Training: No training on customer data.
Logging: Abuse monitoring
Third-party access: None disclosed
GDPR DPA: DPA available
Transfer mechanism: SCCs

Geodd — United States🇺🇸

Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. US; SCCs.

Zero data retention: On by default on Pay-as-you-go.
Training: No training on customer data.
Logging: None
Third-party access: Provider may share with subprocessors / partners
GDPR DPA: No DPA
Transfer mechanism: SCCs

Benchmarks

Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.

Global rank#107 of 531 LLMs

TierEfficient

Output speed35 tok/s

First token1.00s

Intelligence Index29.4

Coding Index38.7

Reasoning & knowledge

GPQA Diamond

86%

Humanity's Last Exam

23%

Long-context reasoning

62%

Coding

SciCode

43%

Agentic & tool use

Terminal-Bench Hard

36%

τ²-Bench Telecom

60%

Math & instruction following

IFBench

76%

See full leaderboard →Benchmarks via Artificial Analysis · View on AA

Get started

Call Gemma 4 31B through the Opper gateway with one API key. Let your coding agent set it up, or call it directly — Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.

Set it up with your agent

Copy this and paste it into your coding agent — Claude Code, Cursor, Codex, and more — and it'll wire up Opper for you.

Or call it directly

1import OpenAI from "openai";
2
3const client = new OpenAI({
4  apiKey: process.env.OPPER_API_KEY,
5  baseURL: "https://api.opper.ai/v3/compat",
6});
7
8const completion = await client.chat.completions.create({
9  model: "gemini/gemma-4-31b",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);