Vertex AI Prediction Endpoints support autoscaling but require customers to specify a **minimum number of replicas**. These replicas stay online at all times to serve incoming traffic. When the minimum value is set too high for real traffic levels, the system maintains idle capacity that still incurs hourly charges. This inefficiency commonly arises when teams: * Use default replica settings during initial deployment, * Intentionally overprovision “just in case” without revisiting the configuration, or * Copy settings from production into lower-traffic dev or QA environments. Over time, unused replica hours accumulate into significant, silent spend.
Vertex AI Endpoints are billed per node-hour based on the machine type provisioned. When the minimum replica count is set higher than actual usage requires, replicas remain active and accrue cost even when idle.
