The European gateway to open AI models.

GDPR compliance depends on your contract and your use, not on a label — but the models labeled EU sovereign give it the strongest footing: they run on providers with no non-EU capital control (OVHcloud and Scaleway today, with dedicated EU servers available on request), outside the CLOUD Act's direct reach, and your prompts only transit our gateway host, Vercel (a US company, Paris region), without being stored. Models we can only serve through US-controlled infrastructure carry the “fast access” label, on the card and in the API response, before you send anything.

It follows the SecNumCloud principle: what matters is not where the servers sit, but who controls the company operating them. A US provider with an EU region is still subject to the CLOUD Act, so it never earns the sovereign label here. That single rule is why there are two explicit tiers instead of one vague “hosted in Europe” claim.

No. The only things written to our database are what billing requires: which model, how many input and output tokens, and the amount charged — never the prompt or the reply. The web console follows the same rule: your conversations stay in your browser. The provider serving the call does see the content — which is precisely why every model carries its jurisdiction label.

No subscription, and no card kept on file. You top up a prepaid balance from €10 and every call draws it down, billed per token — from €0.0068 per 100,000 input tokens on the cheapest sovereign model, VAT included. Once the balance runs out, new calls are refused — no automatic charge. Calls already in flight are still billed, so the balance can dip slightly below zero; that amount comes off your next top-up.

No. The API is OpenAI-compatible: point base_url at https://getfrontiereai.eu/api/v1, swap the key, and your SDK, scripts and tools keep working — streaming included. One key covers the whole catalog instead of one account per model vendor.

A curated selection — 22 live today out of 24 in the catalog, from Qwen3.5 397B and GLM-5.2 to Llama 3.3 70B, Mistral Small 3.2 and Kimi K3. Not every open-source model on the market: an entry is added only once we have verified who serves it, under which licence, and at what real cost.

Yes. There is no company check and no minimum volume: sign in with an email link or Google, top up from €10 and call any model in the catalog with a single key. Individuals get the same infrastructure, sovereignty labels and privacy rules as companies — and once the balance runs out, new calls are simply refused.

Yes — anything that speaks the OpenAI API works with a base URL and a key. We checked exactly where that setting lives in n8n, Microsoft Foundry, LangChain (Python), Vercel AI SDK, Open WebUI, LibreChat and Fleece AI, with step-by-step guides for the platforms that have traps. Tool calling is measured model by model, because an agent cannot work without it.