11ms
From a client in the same metro
62%
Free capacity right now
Dedicated
Reservable on the Dedicated plan
iad1
Use this in routing rules
Peering is direct to the two largest local transit providers, so a request from a client in the metro reaches the gateway in about 11 ms before any inference happens at all. Dedicated capacity is reservable here: a replica held for your workload alone, billed monthly rather than per token.
Every model in the catalogue that fits on a single card is warm here. The largest mixture-of-experts models are not — those live in six regions and requests are routed to the nearest of them, which is stated plainly in the response headers rather than hidden.
Pin a workload here
regions: ["iad1"] residency: "strict" fallback: false
strict means fail rather than route elsewhere