Regional inference now available on AI Gateway
- Source
- vercel.com
- Author
- Walter Korman
- Date

Context
Vercel's AI Gateway lets applications require that model requests run in the US or EU. The application selects a region, and the gateway restricts provider selection accordingly. If no compatible provider can serve the request, it fails instead of sending the data elsewhere. Responses report the serving region, giving developers a way to check what happened. The announcement also says any data retained by the provider stays in the selected region.
This restriction requires explicit configuration. Requests without a regional setting still route globally, so using the gateway alone does not establish a residency requirement.
- inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
“If no model provider can serve it, the request fails rather than running somewhere else.”
“Until now, teams with data residency or compliance requirements had to configure regional routing separately for every provider, with no reliable way to confirm where a request actually ran.”
“The provider sets the regional rate, often around 10% above standard, and AI Gateway passes it through with no markup.”
Checking sign-in…
Loading comments…






