Boundless

Inference locations

Provider API declarations are also available on each model's endpoint API. Direct chat and Responses replies separate advertised availability from serving location in usage.inference_location; the actual serving region remains unknown when not reported.

usage.provider_usage.gateway_region identifies the TrustedRouter gateway, not the provider's inference location. A value such as europe-west4 does not mean the model ran in Europe. usage.inference_location.serving_region remains null when the provider has not reported it. Older gateways may return the gateway-only field as provider_usage.region.

Where the upstream GPUs execute the model, not the provider's headquarters, API ingress, or data storage. ZDR and confidential inference do not by themselves restrict geography.

Declared countries or regions

United States; United Kingdom; European Union (countries unspecified)
October 27 terms, section 3.3, describe provider-wide infrastructure in the US, UK and/or EU; not an exact-model placement receipt.

Can locations change?

No fixed model location or exhaustive EU country list is published; placement can vary within the declared regions.

Provider region pinning

Not verified.

Pinning through TrustedRouter

Not supported by the current TrustedRouter integration.

Infrastructure declaration

US, UK and/or EU infrastructure, provider-declared; no per-request residency commitment.

Evidence

Published infrastructure terms, section 3.3. Reviewed 2026-10-28.

• Infrastructure and data terms

Provider selection alone is not a region pin. TrustedRouter's US provider filter selects company jurisdiction, not GPU location. A regional gateway hostname does not pin a downstream GPU. For a binding residency requirement, confirm the model, region, failover scope and enforced controls before sending sensitive data.