Pricing

Vespa charges by the machine resources allocated to your applications in three dimensions:

Per vcpu hour:	$0.12
Per memory Gb hour:	$0.012
Per disk Gb hour:	$0.0004

In production zones, the resources you allocate are precisely what you specify in services.xml for the duration the application is deployed.

In dev, and test zones, applications will by default be downscaled and you will be charged for the capacity actually used. In test zones, applications will only allocate resources while tests are running.

In addition to machine resource costs, network costs incurred by your application are passed on to you at standard AWS prices. These depend only on how you use your applications.

Quota

By default all Vespa Cloud applications are limited to 5 nodes in size. To increase the quota, contact support@vespa.ai.