--- title: "Claude Haiku 5.5 in the EU: API hosted in Europe" description: "Use 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." canonical: "https://inference.eu/models/claude-haiku-5-5/" language: "en" --- Chat · Anthropic # Claude Haiku 5.5 in the EU, processed in European data centres Claude Haiku 5.5 is Anthropic's small, fast model, released in October 2026 for high-volume work such as classification, extraction, routing and live support, 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 Haiku 5.5 is Claude Haiku 5.5 is a closed model from Anthropic, released on 7 October 2026 as the third model in the Claude 5.5 family. Anthropic describes it as its fastest model to date, built for high-volume, latency-sensitive tasks. It reads text and images and writes text, with a context window of one million tokens and up to 128K tokens per response. Haiku 5.5 supports adaptive thinking, steered by an effort setting whose default is medium. It uses the newer Claude tokenizer, so the same text counts as roughly 30 percent more tokens than on Claude Haiku 4.5. Anthropic gives its reliable knowledge cutoff as June 2026. ## What it does well, and where it falls short Anthropic positions Haiku 5.5 for quick, repetitive work: classification, routing, extraction, summaries, compacting long conversations and writing database queries. Its speed suits interactive uses such as live customer support, and it works well as a subagent that Claude Opus or Sonnet hands smaller coding tasks to. It is the smallest model in the Claude 5.5 family, so it is not the right choice for long, complex reasoning, large refactors or tasks where a wrong answer is costly. For those, use Claude Sonnet 5.5 or Claude Opus 5. A common pattern is to let Haiku 5.5 handle the bulk of requests and pass the hard ones to a larger model. ## Calling Claude Haiku 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. In Claude Code, set `ANTHROPIC_BASE_URL` to the inference.eu host and `ANTHROPIC_AUTH_TOKEN` to your inference.eu key, then use `claude-haiku-5.5` wherever you want the small, fast model. The same model is available through the OpenAI-compatible endpoint, so the OpenAI SDKs, LangChain, LlamaIndex and the Vercel AI SDK work with the model set to `claude-haiku-5.5`. Anthropic advises leaving `temperature`, `top_p` and `top_k` unset for this model. Ask for JSON in your prompt or use tool definitions when you need structured output. ## Claude Haiku 5.5 with data processed in the EU When you call Claude Haiku 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. That matters for high-volume work, where the inputs are often customer messages, tickets and documents that contain personal data. 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 model on inference.eu, billed in euros on one invoice. ## Claude Haiku 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 October 2026 Model ID claude-haiku-5.5 Processing EU data centres Training on your data Never Source [platform.claude.com](https://platform.claude.com/docs/en/models/haiku-5-5/overview) claude-haiku-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-haiku-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 ### Ticket and email triage Classify incoming messages, detect language and urgency, and route each one to the right team, at high volume. - 2 ### Live customer support Answer customers in chat quickly, with your help centre content in the prompt and conversations processed in the EU. - 3 ### Subagents for coding Hand file searches, small edits and summaries to Haiku 5.5 while Claude Sonnet 5.5 or Opus 5 plans the overall task. ## Claude Haiku 5.5: common questions The questions buyers, developers and legal teams ask us most. Something missing? Ask us directly. Yes. On inference.eu, Claude Haiku 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 Haiku 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 Haiku 5.5 has a context window of one million tokens and can write up to 128K tokens in one response. That is far more than most high-volume tasks need, but it lets you include long documents or full conversation histories when you do. Yes. Haiku 5.5 accepts text and images and produces text, so it can classify screenshots, read photos of receipts or describe product images. It does not generate images. Use Haiku 5.5 when you have many short, well-defined requests and speed matters: classification, extraction, routing, short summaries and chat support. Use Sonnet 5.5 for coding, longer writing and agent tasks that need more judgement. Haiku 5.5 uses the newer Claude tokenizer. Anthropic says the same text counts as roughly 30 percent more tokens than on Claude Haiku 4.5. Keep this in mind when you compare usage between the two. Yes. With Claude Code pointed at inference.eu through \`ANTHROPIC\_BASE\_URL\` and your inference.eu key, you can use \`claude-haiku-5.5\` for subagents and small tasks while a larger Claude model handles planning. No. Claude Haiku 5.5 is a closed model and Anthropic does not publish the weights. Use is governed by Anthropic's terms. If you need a small model with open weights, inference.eu also offers gpt-oss-20b and other open models. Yes. Point the OpenAI client at the inference.eu API, use your inference.eu key and set the model to \`claude-haiku-5.5\`. If your code already uses the Anthropic SDK, keep it and change only the base URL, key and model. [Ask a question](https://inference.eu/contact/) ## Related [All models](https://inference.eu/models/#directory) - [Claude Sonnet 5.5Use Anthropic's Claude Sonnet 5.5 on inference.eu: requests processed in EU data centres, one data processing agreement, nothing used for training.Chat](https://inference.eu/models/claude-sonnet-5-5/) - [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/) - [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