---
title: "Claude Sonnet 5.5 in the EU: API hosted in Europe"
description: "Use Anthropic's Claude Sonnet 5.5 on inference.eu: requests processed in EU data centres, one data processing agreement, nothing used for training."
canonical: "https://inference.eu/models/claude-sonnet-5-5/"
language: "en"
---

Chat · Anthropic

# Claude Sonnet 5.5 in the EU, processed in European data centres

Claude Sonnet 5.5 is Anthropic's mid-sized frontier model, released in September 2026, built for everyday coding, agent and business work with a one-million-token context window. On inference.eu you call it with the Anthropic Messages or OpenAI request format, processed in EU data centres and never used for training.

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

1.  01Context window: 1,000,000 tokens
2.  02EU data centres
3.  03Proprietary

## What Claude Sonnet 5.5 is

Claude Sonnet 5.5 is a closed model from Anthropic, released on 28 September 2026 as the second model in the Claude 5.5 family and the successor to Claude Sonnet 5. Anthropic describes it as its best combination of speed and intelligence. It reads text and images and writes text, with a context window of one million tokens and up to 128K tokens per response.

Like the other current Claude models, Sonnet 5.5 uses adaptive thinking, steered by an effort setting. Thinking is on by default, and the lowest setting skips up-front thinking and only reasons between tool calls. Anthropic gives its reliable knowledge cutoff as June 2026. The weights and parameter count are not published.

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

Anthropic positions Sonnet 5.5 for code generation, data analysis, writing, visual understanding and agents that call tools. It is strongest at well-scoped tasks: fixing a bug, adding a feature, turning a spreadsheet into a summary, answering questions about a set of documents. Anthropic reports that it needs fewer tokens than Sonnet 5 for the same work.

For work that needs careful judgement over many steps, such as large refactors or complex research, Anthropic points to its Opus models instead. For very high volumes of simple requests, Claude Haiku 5.5 is the cheaper and faster choice. Sonnet 5.5 sits between the two and is a sensible default for most teams.

## Calling Claude Sonnet 5.5 through the API

inference.eu speaks the Anthropic Messages format, so the official Anthropic SDKs work once you change the base URL and the key. To use it in Claude Code, set `ANTHROPIC_BASE_URL` to the inference.eu host, `ANTHROPIC_AUTH_TOKEN` to your inference.eu key, and choose `claude-sonnet-5.5` as the model.

The model is also available through the OpenAI-compatible endpoint, so the OpenAI SDKs, LangChain, LlamaIndex and the Vercel AI SDK work with the model set to `claude-sonnet-5.5`. Images go in as content parts next to your text. Anthropic advises against setting `temperature`, `top_p` or `top_k` for this model, so leave them out of your requests.

## Claude Sonnet 5.5 with data processed in the EU

When you call Claude Sonnet 5.5 on inference.eu, your prompts, images 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 every Claude model and every other model on inference.eu, and everything is billed in euros on one invoice.

## Claude Sonnet 5.5

Maker

Anthropic

Made in

United States

Type

Chat

Context window

1,000,000 tokens

Licence

[Proprietary](https://www.anthropic.com/legal/commercial-terms)

Released

September 2026

Model ID

claude-sonnet-5.5

Processing

EU data centres

Training on your data

Never

Source

[platform.claude.com](https://platform.claude.com/docs/en/models/sonnet-5-5/overview)

claude-sonnet-5.5 · 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="claude-sonnet-5.5",
    messages=[{"role": "user", "content": "Summarise this contract in five bullet points."}],
)
print(response.choices[0].message.content)
```

## What teams use it for

-   1

    ### Everyday coding

    Fix bugs, write tests and add features in your editor or in Claude Code, with source code processed in the EU.

-   2

    ### Business assistants

    Answer questions about contracts, policies and reports, and draft emails and summaries in English, German, French and other languages.

-   3

    ### Agents with tools

    Build agents that search, call your internal APIs and read screenshots, using the tool calling you already use with Claude.

## Claude Sonnet 5.5: common questions

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

Yes. On inference.eu, Claude Sonnet 5.5 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 Sonnet 5.5 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 Claude or any other model.

Claude Sonnet 5.5 has a context window of one million tokens and can write up to 128K tokens in one response. Everything in the request counts towards the window, including images, tool definitions and the model's thinking.

Yes. Sonnet 5.5 accepts text and images and produces text. It reads screenshots, charts, diagrams and scanned pages. It does not generate images.

Set \`ANTHROPIC\_BASE\_URL\` to the inference.eu host and \`ANTHROPIC\_AUTH\_TOKEN\` to your inference.eu key, then select \`claude-sonnet-5.5\` as the model. Claude Code then sends your prompts and source code to inference.eu, where they are processed in EU data centres.

Yes. Point the OpenAI client at the inference.eu API, use your inference.eu key and set the model to \`claude-sonnet-5.5\`. Messages, streaming and tool calls use the usual OpenAI format. The Anthropic Messages format is available too.

Start with Sonnet 5.5 for most coding, writing and agent work. Move hard, long-running tasks that need careful judgement to Opus 5, and high-volume, simple tasks such as classification or routing to Haiku 5.5. Testing on your own prompts is the only reliable way to decide.

No. Claude Sonnet 5.5 is a closed model and Anthropic does not publish the weights. Use is governed by Anthropic's terms. If you need open weights, inference.eu also offers models such as gpt-oss-120b and DeepSeek V4.1 Flash.

Anthropic's documentation says that setting \`temperature\`, \`top\_p\` or \`top\_k\` on Claude Sonnet 5.5 returns an error. Remove those parameters and steer the output through your prompt and the effort setting instead.

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

## Related

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

-   [Claude Opus 5Use Anthropic's Claude Opus 5 on inference.eu: requests processed in EU data centres, one data processing agreement, and nothing used for training.Reasoning](https://inference.eu/models/claude-opus-5/)
-   [Claude Haiku 5.5Use Anthropic's Claude Haiku 5.5 on inference.eu for high-volume tasks: requests processed in EU data centres, one DPA, nothing used for training.Chat](https://inference.eu/models/claude-haiku-5-5/)
-   [gpt-oss-120bRun OpenAI's open-weight gpt-oss-120b reasoning model on inference.eu: the OpenAI API format, with requests processed in EU data centres, billed in euros.Reasoning](https://inference.eu/models/gpt-oss-120b/)
-   [DeepSeek V4.1 Flash (1017)Run DeepSeek V4.1 Flash (1017) on inference.eu: a multimodal open reasoning model with 1M context, OpenAI-compatible, processed in the EU, not in China.Reasoning](https://inference.eu/models/deepseek-v4-1-flash-1017/)

## 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