Understanding Compute Sources

Shared Compute: Kinesis-managed, multi-tenant, pay-per-use The primary benefit is that applications enjoy full access to the machine's capabilities, while costs are incurred only for actual usage, measured by:

• CPU milliseconds consumed

• GPU milliseconds consumed

• RAM and VRAM bytes used

When an application is idle and not utilizing CPU or GPU resources, no corresponding charges apply. This mode is well-suited for rapid prototyping and non-critical workloads where consistent performance is not essential.

Server Pools: Compute you control—either provisioned by Kinesis or connected from your own infrastructure. Can be shared across apps or accounts.

Server pools consist of dedicated resources managed by you or your company’s system administrators. These resources are shared only within the same organization. They are billed based on the time they are reserved. Charges occur as follows:

• Full price when active: Servers are considered active when they have one or more apps that are not in the “Stopped” state (e.g. they are “Running” or “Starting”)

• Storage-only price when hibernated: If a server has no apps on it, or if all apps are in the stopped state, Kinesis hibernates it to save on costs. In this case, charges apply only to storage.

💡An app can access multiple pools, expanding its resource options.

ℹ️ If your organization already has some server pools set up for you, you probably want to use them in most cases. Check with your system administrator to confirm.