Each tenant in Vespa Cloud has a quota that limits the amount of resources you can use. The quota is expressed as $/hour, and is based on the maximum possible cost for a Vespa application. That means if you are using autoscaling the quota it will use is based on the maximum configured size of the application.
You can see how much quota your applications are using in the Vespa Cloud console.
The quota your tenant has depends on the plan the tenant is on:
|Pay as you go||$125/h|
If you are on a paid plan and want to change the quota, please contact Vespa Cloud Support.