> ## Documentation Index
> Fetch the complete documentation index at: https://docs.nebius.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Pricing and quotas in Serverless AI

Serverless AI does not have its own quotas and pricing; the service applies the quotas and pricing of Compute:

* When you create endpoints or jobs, they count towards Compute quotas.
* As endpoints and jobs are based on virtual machines (VMs), you are charged for endpoints and jobs as for VMs.

In addition, if you mount an [Object Storage bucket](/object-storage/overview#buckets) or a [shared filesystem](/compute/storage/types#shared-filesystems) to an endpoint or job, separate billing for the bucket and filesystem applies.

If you add an SSH key to a job or enable a static public IP address for an endpoint, the platform allocates a public address. As a result, this counts towards the quota of public IP addresses per region.

For more information about the quotas and pricing, see:

* [Quotas of VMs and filesystems](/compute/resources/quotas-limits)
* [Quota of public addresses](/vpc/resources/quotas-limits)
* [Pricing for VMs and shared filesystems](/compute/resources/pricing)
* [Pricing for buckets](/object-storage/resources/pricing)