Product
Solutions
Resources
Zero data retention, in the EU
Prompts and outputs are never stored or used for training, and the entire chain sits under European law. Almost nobody offers that combination.
Some US AI providers offer zero data retention. Some European providers offer EU hosting. The combination of the two, prompts that are never kept anywhere plus a chain that sits entirely under European law, is claimed by almost nobody. Yet that is exactly what you want once customer records, medical information or confidential documents start flowing through your prompts.
HostYourAI delivers both at once: an OpenAI-compatible LLM API on GPUs in European data centers, with no storage of prompts and outputs, and a data processing agreement underneath it.
What zero data retention means here
Your prompts and the generated responses are processed, returned, and that is the end of it. They are not stored for training or reuse. There is no dataset slowly filling up with your conversations, no human review programme sampling them, and no vague "improving our services" clause that quietly means training. The guarantee that we never train on customer data is written into the data processing agreement.
EU Inference Router
‹ Insight 1 of 28 ›What we do record, and why
Complete invisibility does not exist with a paid API, and anyone promising it is not being honest with you. For billing and observability we record metadata per request: timestamp, the model used, token counts and latency. You see that data in your own activity log, and you can configure how much detail it keeps. What is not retained: the content of your prompts and outputs for training or analysis purposes.
You need that metadata yourself anyway. Without token counts there is no cost control, without latency figures no performance insight, and without a request log no answer to what went wrong yesterday at 14:32.
from openai import OpenAI client = OpenAI( base_url="https://hostyourai.com/api/v1", api_key="hyai-...") client.chat.completions.create( model="llama-3.3-70b", messages=[{"role":"user","content":"Hallo!"}])
Why the combination with EU jurisdiction matters
Zero retention at a US provider is a promise made inside a legal system that can override it. The US CLOUD Act allows American authorities to compel US companies to hand over data, wherever that data lives. A retention policy is a setting; jurisdiction is a fact. At HostYourAI that tension does not exist: a Dutch company, European data centers, and no US subprocessor in the inference chain. More background is on our AI data sovereignty and AI compliance in Europe pages.
The data that does exist, such as account details and billing metadata, is encrypted with AES-256. The platform runs under a 99.9% SLA.
EU Inference Router
‹ Insight 1 of 28 ›Connect without rebuilding
The API speaks OpenAI's /v1/chat/completions format, streaming included. If you work with the Anthropic SDK, there is a /v1/messages endpoint with x-api-key authentication. Switching means changing your base_url and key, nothing more.
curl https://hostyourai.com/api/v1/chat/completions \
-H "Authorization: Bearer hyai-..." \
-H "Content-Type: application/json" \
-d '{
"model": "llama-3.3-70b",
"messages": [{"role": "user", "content": "Anonymise this case file excerpt."}]
}'Questions about zero data retention
Are my prompts really not stored anywhere?
The content of prompts and outputs is not stored for training or reuse and is not shared with third parties. What remains is billing metadata: timestamp, model, token counts and latency.
What exactly is in the activity log?
Per request, the metadata you need for cost tracking and debugging: time, model, tokens and latency. The level of detail is configurable, so you decide how much context is kept.
Do you or your suppliers train on my data?
No. Nobody in the chain ever trains on customer data. That commitment is in the data processing agreement, and our subprocessors are listed on a public page.
How is this different from zero retention at a US provider?
The retention policy may sound identical, but the jurisdiction is fundamentally different. A US company remains subject to the US CLOUD Act regardless of what its policy says. Here, the entire chain sits under European law.
Does zero retention also apply to dedicated GPU instances?
Yes. On a dedicated instance your model runs on a vLLM server that is yours alone, also in a European data center, with the same guarantees.
Everything you need for AI
From model hosting to a customer-facing API, it is built for developers and businesses who want their AI running on infrastructure they actually control, inside the EU.
Your data and your models stay on European GPUs. GDPR-friendly by design.
Llama, Qwen, DeepSeek, Mistral, FLUX and plenty more. Pick one and it is warm in minutes, with no DevOps on your end.
Point your existing client at the Router and keep your tools. No rewrite, no lock-in.
From zero to a warm endpoint in minutes
No infra to manage. Pick a model, get an OpenAI-compatible URL, ship.
Pick a model
Choose from the Model Garden or paste any HuggingFace ID. Set the VRAM and pick an EU GPU.
Get your endpoint
We deploy vLLM, run readiness probes, and hand you a warm OpenAI- and Anthropic-compatible URL plus an API key.
Route and ship
Point your client at the Router. It auto-routes to a warm instance, idles GPUs when nobody is online, and logs every request.
Works with the tools you already use
The Router speaks the OpenAI and Anthropic APIs, so it drops straight into the clients and SDKs your team already runs. Just change the base URL.
Try HostYourAI for free
Built for teams that can't send data away
If a US cloud is off the table, HostYourAI gives you the same developer experience on European infrastructure.
Citizen data that legally has to stay in the EU, with full auditability.
Finance, healthcare and legal teams under GDPR, DORA and the AI Act.
Ship AI features your customers trust, without a US sub-processor.
Deliver private AI for clients on infrastructure you can stand behind.
Frequently asked questions
Can I run this in the EU?
Yes. HostYourAI runs open models on GPUs in European datacenters via vLLM. Your prompts and outputs never leave the EU and there is no US cloud provider in the chain.
Is it GDPR-compliant?
Yes. All processing happens inside the EU, a Data Processing Agreement (DPA) is available and the subprocessor list is public. Open weights also mean no training on your data.
Is the API OpenAI-compatible?
Yes. Point your existing OpenAI or Anthropic client at our Router (https://hostyourai.com/api/v1), change only the base URL and API key. No rewrite, no lock-in.
What does it cost?
Pay-as-you-go on one prepaid credit balance: the shared router per token or a dedicated GPU per hour. Free to start, no minimum, no fixed monthly fee.
Works with 390+ open models
Text and image models on dedicated EU GPUs. Every model tested on our own hardware.
Related pages
Explore more about EU-hosted AI on HostYourAI.
AI for lawyers and legal teams on European GPUs. Confidential documents stay in the EU, with open models and a Data Processing Agreement.
Read more →AI hosting that meets all GDPR requirements. Data stays in the EU, no US transfers, Data Processing Agreement included. For compliance-conscious companies.
Read more →Host Llama 3 and Llama 3.3 on dedicated NVIDIA GPUs in Europe. OpenAI compatible API, one-click deployment, GDPR compliant.
Read more →Host DeepSeek R1 in European data centers. Advanced reasoning capabilities, GDPR compliant, dedicated GPU instances.
Read more →Machine learning hosting on dedicated GPUs. Training, inference, fine-tuning - all on European infrastructure.
Read more →Featherless offers thousands of models but no EU guarantee. HostYourAI hosts open models on European GPUs with GDPR compliance, a DPA and clear pricing.
Read more →