Endpoint cost multiplies hourly rate by replicas and scale-up hours
Catalog row in Vendor License Rules · Cited
- Kind
- Counting
- Statement
- Inference Endpoints pricing documentation: cost is the instance hourly rate times minimum-replica hours plus scale-up hours times additional replicas.
- Applies when
- Forecasting autoscaled Endpoint cost
- Applies to
- Inference Endpoints
- Related metrics