Does gemma-4-31B-it-Ultra support zero data retention?

Yes. gemma-4-31B-it-Ultra is available with zero data retention on DeepInfra through the Opper gateway.

Where is gemma-4-31B-it-Ultra hosted?

gemma-4-31B-it-Ultra runs on US hosting routes through the Opper gateway.

Is gemma-4-31B-it-Ultra trained on prompts and outputs?

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

Is a GDPR DPA available for gemma-4-31B-it-Ultra?

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

gemma-4-31B-it-Ultra

by Google

Gemma 4 31B IT Ultra is a serving variant of Google DeepMind's instruction-tuned Gemma 4 31B, the dense 30.7 billion parameter model that is the largest in the Apache 2.0 licensed Gemma 4 family released on April 2, 2026. The Ultra build is a speed-focused profile of the standard model, running in FP8 precision with a 131,072 token context window, half the 256K window of the full-precision checkpoint. It keeps the model's capabilities intact: text and image input, a built-in thinking mode toggled by control tokens, and native function calling, alongside the multilingual coverage of the Gemma 4 family. The underlying full-precision model reports 85.2% on MMLU Pro, 80.0% on LiveCodeBench v6, and 89.2% on AIME 2026 without tools. The variant suits high-volume chat, extraction, and agent steps where per-request latency matters more than the longest possible context, and where a dense 31B open model is already sufficient for the task.

Call gemma-4-31B-it-Ultra on Opper with the OpenAI SDK. Sign up without a credit card. Get started

Get your API key Try in chat Compare

Key info

Input

Output

Features

Context window

131K

Max output

131K

Input price

$0.27 /1M

Output price

$0.76 /1M

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

Available routes

gemma-4-31B-it-Ultra runs on 1 route through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below.

Provider	Region	Zero data retention	Training	Input	Output	Cache read
DeepInfra	US		No	$0.27	$0.76	Input price

Live routes and prices as JSON: api.opper.ai/v3/models?q=deepinfra%2Fgoogle%2Fgemma-4-31B-it-Ultra

Uptime and availability

gemma-4-31B-it-Ultra 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-4-31B-it-Ultra 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: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; unknown; DPA available.

Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
Training: No training on customer data.
Logging: None
Abuse monitoring: No classifier
GDPR DPA: DPA available
Transfer mechanism: unknown

Get started

Call gemma-4-31B-it-Ultra through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

gemma-4-31B-it-Ultra is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

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-4-31B-it-Ultra",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);