Does Gemma 3 4B IT support zero data retention?

Yes. Gemma 3 4B IT is available with zero data retention by default on DeepInfra through the Opper gateway.

Where is Gemma 3 4B IT hosted?

Gemma 3 4B IT runs on US hosting routes through the Opper gateway.

Is Gemma 3 4B IT trained on prompts and outputs?

No. Every hosting route for Gemma 3 4B IT is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Gemma 3 4B IT?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Gemma 3 4B IT. Contact hello@opper.ai to receive it.

Gemma 3 4B IT

by Google

Gemma 3 4B IT is one of the smaller instruction-tuned models in the Gemma 3 family, with 4 billion parameters sized for on-device and edge use. It carries a 128K token context window, supports comprehension across more than 140 languages, and is small enough to deploy on laptops, desktops, and resource-constrained environments. The model is instruction-tuned for text generation and understanding, including question answering, summarization, and reasoning, and can follow structured prompts for tool-style workflows. Its compact footprint makes it well suited to privacy-sensitive and bandwidth-constrained applications. It is released under the Gemma license, which permits commercial use.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

131K

Max output

131K

Input price

$0.05 /1M

Output price

$0.10 /1M

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

Available routes

Gemma 3 4B IT runs on 1 route 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
DeepInfra	US	Zero data retention	No	$0.05	$0.10

Uptime and availability

Gemma 3 4B IT runs on a single route through the Opper gateway today, so its availability is that provider's availability.

100%route uptime, last 30 days

Single route, no failover target within this model.

Name a second model in the same request and the gateway tries it on retriable errors, so a busy hour never has to reach your users. Set up a fallback chain.

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. See uptime for every provider Opper monitors.

Data handling per route

Each route hosting Gemma 3 4B IT has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

DeepInfra — United States🇺🇸

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

Zero data retention: On by default on Pay-as-you-go.
Training: No training on customer data.
Logging: None
Third-party access: None disclosed
GDPR DPA: DPA available
Transfer mechanism: unknown

Get started

Call Gemma 3 4B IT 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 a coding agent like Claude Code, Cursor or Codex 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: "deepinfra/google/gemma-3-4b-it",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);