Sovereign AI gateway: one API, all your models, costs centralized

The gateway exposes one endpoint, in the OpenAI API format. Your applications talk to it as they would to OpenAI; behind it, the gateway distributes requests across several open source models hosted in Europe.

• Mistral: an open-weight European model, capable and commercially licensed.
• Llama, Qwen, GLM, DeepSeek: to cover other task profiles such as reasoning, code, long context and multilingual.
• One API contract for all of them: you switch models by changing a parameter, without rewriting your code.

Your existing tools (OpenAI SDK, libraries, agents) work without adaptation: the base URL and the key change, while your code stays as is.

Not every request deserves the biggest model. The gateway applies cost-aware routing: a simple task (classification, extraction, short summary) goes to a small, fast, cheap model; a demanding task goes to a more capable one.

• Weighted distribution: you split traffic across several models by weight, for example to test a new model on a fraction of calls.
• Local ↔ EU cloud failover: if the targeted sovereign model is unavailable, the request can fail over to another sovereign instance, another European region or a model hosted in the EU.
• A gain you measure: tuned well, this routing can reduce latency and the volume of billed tokens, depending on your request mix. The gain depends on your real usage and shows up in measurement, with no figure promised up front.

Without guardrails, a generative-AI bill drifts fast, and no one knows which team consumes what. The gateway centralizes that governance.

• Virtual keys: each team, project or application gets its own key, without exposing the credentials of the underlying models.
• Caps and budgets: you set a monthly budget or a spend cap per key. Beyond it, calls are refused rather than letting the bill run.
• Consolidated costs: consumption across all models is aggregated in one place, broken down by team and project. The CIO and CFO see a single consolidated cost line instead of ten scattered invoices.

That turns "we don't know what AI costs us" into a metric you can steer, the way FinOps does for cloud.

The gateway sits in the path of every request. That position lets you apply controls before the prompt reaches a model.

• In-path inspection: calls go through a single point where you can log, filter and apply rules.
• Fail-closed on personal data: the default posture is to refuse rather than let through. If a routing rule cannot be satisfied while staying sovereign, the request is blocked instead of being redirected outside Europe.

This is a security posture, a set of configured rules; it is not an absolute guarantee. It reduces the margin for error; it does not replace your own risk analysis.

A gateway is only worth what it routes to. Here, the gateway and the models it calls stay in Europe.

• The entry point is hosted on European infrastructure.
• The target models run on GPUs hosted in the EU, out of reach of the US CLOUD Act.
• Failover stays bounded to sovereign instances, with no silent switch to a third-party API outside the EU.

A sovereign AI gateway controls the data path end to end, where a generic gateway stops at the entrance.

This gateway is the routing and governance layer of our Private GPT, our chat and RAG app, ready for your teams.

Private GPT provides the interface (chat, RAG over your documents, access management); the gateway brings the multi-model routing, cost-aware routing and cost governance underneath. You can also call the gateway directly from your own applications.