> For the complete documentation index, see [llms.txt](https://docs.kinesis.network/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.kinesis.network/getting-started/running-llms-with-kinesis-network/understanding-compute-sources.md).
# Understanding Compute Sources
{% hint style="info" %}
Skip this section if your administrator shares Grids with your account.
{% endhint %}
**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.
**Grids: Compute you control—either provisioned by Kinesis or connected from your own infrastructure. Can be shared across apps or accounts.**
Grids 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.
{% hint style="info" %}
Use your organization’s existing grids when available. Confirm the appropriate pool with your system administrator. Please see next section on how to use Grids assigned to you.
{% endhint %}
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://docs.kinesis.network/getting-started/running-llms-with-kinesis-network/understanding-compute-sources.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.