Regional processing (Europe rule)
Regional processing is a routing rule that lets AI requests be served only by inference endpoints in an approved region. A Europe rule is the European version: requests go only to European endpoints and are refused when none is available.
Why it matters for companies
A region setting that quietly falls back to another region on errors or retries protects less than it appears to. The rule has to hold for every call that carries the prompt: classification, the answer, retries and fallbacks.
Refusing a request is the safe outcome. A clear error is easy to handle, while a silent transfer outside the region is a compliance incident.
Example
A public-sector team sets a Europe rule on its keys. When the only European endpoint for a model is down, the request returns an error and the team switches to another model, with nothing served in the US.
How Standard Compute handles it
Set a Europe rule for your company, a team or a single key, and every request, including retries and fallbacks, is served only by approved European inference endpoints. If no European endpoint can serve it, the request is refused before your prompt is sent.
Our EU gateway terminates TLS and runs in Finland, and your account data is stored in Frankfurt.