---
title: "Gemini 4 Argon in the EU: API with EU data residency"
description: "Use Google's Gemini 4 Argon on inference.eu: requests processed in EU data centres, one data processing agreement, and nothing used for training."
canonical: "https://inference.eu/models/gemini-4-argon/"
language: "en"
---

Reasoning · Google DeepMind

# Gemini 4 Argon in the EU, processed in European data centres

Gemini 4 Argon is Google's flagship reasoning model, generally available since October 2026, built for complex software engineering, maths, science and long multi-step agents, with a context window of about one million tokens. On inference.eu you call it through an OpenAI-compatible API, processed in EU data centres and never used for training.

[Contact sales](https://inference.eu/contact/)[Example request](#example)

1.  01Context window: 1,048,576 tokens
2.  02EU data centres
3.  03Proprietary

## What Gemini 4 Argon is

Gemini 4 Argon is a closed frontier model from Google DeepMind. Google announced it on 30 September 2026 with access for a small group of testers and made it generally available to developers on 13 October 2026. It accepts text, images, video, audio and PDF documents and produces text.

The context window is 1,048,576 tokens, shared between input and output. By default a single response can be up to 65,536 tokens; Google also designed the model for very long outputs of hundreds of thousands of tokens. Thinking is adjustable in three levels, low, medium and high, with medium as Google's default. Google does not publish the weights or the parameter count.

## What it does well, and where it falls short

Google built Argon for hard problems that take many steps: real-world software engineering, large code migrations, mathematical and scientific problem solving, and autonomous agents. Google also highlights enterprise knowledge work such as legal research and drafting and financial research, reading charts and long documents, and finding and patching security vulnerabilities.

That depth has a cost. At high thinking levels Argon reasons at length, so responses take longer and use more output tokens than a Flash model. For routine chat, short extraction or high request volumes, Gemini 3.8 Flash is usually the better fit, and you can move to Argon only for the tasks that need it.

## Calling Gemini 4 Argon through the API

inference.eu speaks the OpenAI request format, so the OpenAI SDKs for Python and JavaScript, LangChain, LlamaIndex and the Vercel AI SDK work as they are. Set the base URL to the inference.eu API, use your inference.eu key and set the model to `gemini-4-argon`. Tools and agents that use the Anthropic Messages format can call the same model there.

Send images as `image_url` content parts alongside your text. Tool calls, JSON output and streaming work as usual. If you plan to send audio, video or PDF files, or need responses longer than 65,536 tokens, get in touch first so we can confirm the request format for your account.

## Gemini with EU data residency

When you call Gemini 4 Argon on inference.eu, your prompts, files and the model's responses are processed in data centres in the European Union. They are used to answer your request and are never used to train any model.

We sign one data processing agreement under Article 28 of the GDPR with every customer and provide our list of subprocessors, so your data protection officer can see who handles the data and where. The same agreement covers Gemini, Claude and every open model on inference.eu, all billed in euros on one invoice.

## Gemini 4 Argon

Maker

Google DeepMind

Made in

United States

Type

Reasoning

Context window

1,048,576 tokens

Licence

[Proprietary](https://ai.google.dev/gemini-api/terms)

Released

October 2026

Model ID

gemini-4-argon

Processing

EU data centres

Training on your data

Never

Source

[ai.google.dev](https://ai.google.dev/gemini-api/docs/models/gemini-4-argon)

gemini-4-argon · Python

```
import os
from openai import OpenAI

client = OpenAI(base_url="https://api.inference.eu/v1", api_key=os.environ["INFERENCE_EU_API_KEY"])

response = client.chat.completions.create(
    model="gemini-4-argon",
    messages=[{"role": "user", "content": "Summarise this contract in five bullet points."}],
)
print(response.choices[0].message.content)
```

## What teams use it for

-   1

    ### Large code migrations

    Let an agent work through big codebases over many steps, planning changes, running tools and checking the results, with source code processed in the EU.

-   2

    ### Legal and financial analysis

    Research and draft across long contracts, filings and reports that include tables and charts, where careful reasoning matters more than speed.

-   3

    ### Security review

    Have the model look for vulnerabilities in your own code and propose fixes, with the code staying in EU data centres.

## Gemini 4 Argon: common questions

The questions buyers, developers and legal teams ask us most. Something missing? Ask us directly.

Yes. On inference.eu, Gemini 4 Argon is served from EU-only endpoints and your requests are processed in data centres in the European Union. You get one data processing agreement for all models and one invoice in euros.

Whether your use is lawful depends on what you process and why, not on the model alone. On inference.eu, requests are processed in EU data centres, are not used for training, and are covered by a data processing agreement under Article 28 of the GDPR with a published subprocessor list. That gives you the contractual basis to use Gemini 4 Argon with personal data.

No. What you send to inference.eu is used only to produce your response. It is not used to train or fine-tune Gemini or any other model.

Gemini 4 Argon has a context window of 1,048,576 tokens, shared between input and output. By default a response can be up to 65,536 tokens. Images, documents and the model's thinking all count towards the window.

Google announced Gemini 4 Argon on 30 September 2026 and first gave access to a small group of testers. It became generally available to developers on 13 October 2026.

Google lists text, images, video, audio and PDF as inputs, and text as output. On inference.eu, text and images work through the standard OpenAI message format. Contact us before building on audio, video or PDF input so we can confirm the format for your account.

Argon has three thinking levels: low, medium and high, with medium as the default. Low answers faster and uses fewer tokens; high reasons longer on hard problems. Pick the lowest level that gives correct results for your task.

Use Gemini 3.8 Flash for most everyday work and high volumes. Use Argon for the hardest tasks: long agent runs, complex coding, deep research and analysis where quality matters more than speed. Testing both on your own prompts is the quickest way to decide.

No. Gemini 4 Argon is a closed model and Google does not publish the weights. Use is governed by Google's terms. Google's open models are the Gemma family; Gemma 4 31B and Gemma 4 26B A4B are also available on inference.eu.

Yes. Change the base URL to the inference.eu API, use your inference.eu key and set the model to \`gemini-4-argon\`. Your messages, tools and streaming code stay the same.

[Ask a question](https://inference.eu/contact/)

## Related

[All models](https://inference.eu/models/#directory)

-   [Gemini 3.8 FlashUse Google's Gemini 3.8 Flash on inference.eu: a fast model with 1M context, requests processed in EU data centres and nothing used for training.Chat](https://inference.eu/models/gemini-3-8-flash/)
-   [Gemma 4 31BRun Google's Gemma 4 31B on inference.eu: an open multimodal model with 256K context behind an OpenAI-compatible API, processed in EU data centres.Vision](https://inference.eu/models/gemma-4-31b/)
-   [Gemma 4 26B A4BRun Google's Gemma 4 26B A4B on inference.eu: a fast mixture-of-experts model with image input and 256K context, processed in EU data centres.Vision](https://inference.eu/models/gemma-4-26b-a4b/)

## Move your AI workloads to EU infrastructure

Tell us which models you use and roughly how much traffic you have. We reply within one working day with pricing and next steps.

-   Reply within one working day
-   Pricing for your volume
-   DPA ready to sign