Skip to main content
Serverless AI does not have its own quotas and pricing; the service applies the quotas and pricing of Compute. When you create Devlabs, endpoints or jobs, they count towards Compute quotas. Billing depends on whether the deployment is running or stopped:
  • While a Devlab, job or endpoint is running, you are billed for its computing resources and storage under Compute VM and disk pricing.
  • While a Devlab is stopped, you are billed for the entire container disk, but not for computing resources. Jobs cannot be stopped.
  • While an endpoint is stopped, you are not billed for computing resources or storage.
In addition, if you mount an Object Storage bucket or a shared filesystem to a Devlab, endpoint or job, separate billing for the bucket and filesystem applies, including when the deployment is stopped. If you add an SSH key to a Devlab or 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: