AI API Europe
OpenAI compatible AI API running entirely in Europe.
An AI API in Europe should be judged like any other API: by its endpoints, its compatibility and how fast you reach a working request. HostYourAI's API is OpenAI-compatible at https://hostyourai.com/api/v1, authenticated with keys that start with hyai-, and it serves open models like Qwen, Llama, Mistral and DeepSeek with vLLM on European GPUs.
The EU part is not a footnote. Every request is processed in European datacenters, which means the API you build against for convenience is also the one your compliance team can approve: DPA available, public subprocessor list, no training on your data.
Why an AI API in Europe in the EU
Latency where your users are
Streamed tokens generated in Europe arrive at European clients over a short network path. For interactive products, where perceived speed is the time to the first token, keeping inference on the continent is the cheapest performance win you will find.
One privacy answer for every feature
Build every AI feature on an EU-processed API and the data protection story is answered once, centrally, instead of per feature. Prompts stay in the EU, encrypted in transit with TLS and at rest with AES-256, and are never used for training.
Open models keep you portable
The API serves open-weight models, so the thing you depend on is a standard interface plus public weights, not a proprietary black box. If your needs change, you switch models in the model catalog or move to dedicated GPU instances without touching client code.
EU Inference Router
‹ Insight 1 of 28 ›Endpoints and compatibility in detail
The core is POST /v1/chat/completions, matching the OpenAI schema: messages, temperature, max_tokens, and SSE streaming with stream: true. Official OpenAI SDKs work by setting the base URL. Non-streaming responses can also carry a sources array with citations when a knowledge base is linked, as described in Build RAG on EU GPUs.
For code written against the Anthropic SDK there is a /v1/messages shim: it authenticates with an x-api-key header, handles text-only messages, and returns streaming in buffered form. You can try every model in the Playground before writing code, and the per-request activity view shows what each call consumed. Usage is billed per token from a prepaid credit balance; see the pricing page.
| Endpoint | What it does |
|---|---|
| POST /v1/chat/completions | OpenAI-style chat completion, hyai- bearer key |
| POST /v1/chat/completions with stream: true | Token-by-token output over SSE |
| POST /v1/messages | Anthropic-compatible shim, x-api-key auth, text-only, buffered streaming |
| GET /v1/models | Lists the models your key can call |
| knowledge_base_id in the request body | Injects RAG context from a linked knowledge base into the completion |
How to start
Generate a key in the dashboard for the EU Inference Router, then make your first streaming call.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://hostyourai.com/api/v1",
apiKey: "hyai-...",
});
const stream = await client.chat.completions.create({
model: "qwen3-32b",
messages: [{ role: "user", content: "Write a haiku about servers in Europe." }],
stream: true,
});
for await (const chunk of stream) {
process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}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!"}])
Questions about an AI API in Europe
Which SDKs work out of the box?
Any OpenAI SDK that lets you set a base URL. Code written for the Anthropic SDK can use the /v1/messages shim with x-api-key auth.
How does streaming behave?
/v1/chat/completions streams over SSE exactly like OpenAI's API. The Anthropic-compatible /v1/messages endpoint streams in buffered form and supports text-only content.
How do I see what a request cost?
The activity view logs usage per request, and everything draws from one prepaid balance topped up with iDEAL, card or SEPA.
Can the API ground answers in my own data?
Yes. Link a knowledge base to the Router or an instance, or pass knowledge_base_id in the request body, and relevant context is injected automatically. Non-streaming responses include source citations.
Is there a way to test without writing code?
Yes, the Playground in the app lets you chat with any catalog model and tune parameters before you integrate the API.
What availability can I plan for?
The platform carries a 99.9% uptime SLA, and popular models stay warm in a pool so first tokens are not delayed by cold starts.
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.
Private by Default
HostYourAI keeps your models, prompts and data on European GPUs. It is built for teams that care about compliance, reliability and real control.
GPUs and data residency inside Europe. Your prompts never leave the EU.
Run open-weight models with no black boxes or hidden telemetry.
GPUs idle when nobody is online, so you only pay for what you run.
Your infra, your keys, your models. Leave whenever you want.
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
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 government and the public sector on European GPUs. Citizen data stays in the EU, with a DPA, open models and full auditability.
Read more →Looking for a RunPod alternative in Europe? HostYourAI runs managed vLLM on EU GPUs under European law: a ready API instead of bare GPUs.
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 →Ollama for local work, HostYourAI for production: the same open models behind a hosted OpenAI-compatible API on EU GPUs. Swap your base_url and go live.
Read more →Host DeepSeek Coder V2 on dedicated NVIDIA A100 80GB in European data centers. GDPR compliant, pay-as-you-go, OpenAI-compatible API.
Read more →Host Llama 3.1 8B on dedicated NVIDIA A10 in European data centers. GDPR compliant, pay-as-you-go, OpenAI-compatible API.
Read more →