Pricing & billing that’s best for you
When your prediction completes successfully, we calculate how long it ran for, and add it to your account. Once per week we charge you for the time that you’ve used. You can find your current usage on your account page.
No worries about provisioning and managing GPU servers. We handle it all and provide one-click templates to get your model up and running effortlessly.
No need to manually adjust GPU resources based on load. Our system automatically scales the allocated GPUs to meet your needs.
Leave the deployment to us. Focus on your model without worrying about the complexities.
ModelZ automatically scales down the allocated GPUs to zero when your AI model deployment is idle and not making predictions for a certain period of time.
Questions you might have regarding billing, cancellation, etc.