Sail Research

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

Global (countries unspecified)
Sail documents multi-region processing by default, including outside the United States.

Can locations change?

Country is unrestricted unless a supported account sends the US-only routing option.

Provider region pinning

Pro and Enterprise accounts can request routing.allowed_countries=[US]; unavailable US capacity fails closed. Surcharges apply.

Pinning through TrustedRouter

Not supported by the current TrustedRouter integration.

Infrastructure declaration

Global, dynamically placed; TrustedRouter does not enforce Sail's US-only option.

Evidence

Public security and US-only inference documentation. Reviewed 2026-10-28.

• Data processing and residency
• Provider US-only option

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.