> 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.md).

# Deploy an app

Choose a source, configure your app and verify its first deployment.

An app is a container workload inside a project. You can start with a curated template, a container image or a GitHub repository. The same concepts apply to model serving, web services and background jobs.

## Choose your starting point

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>App Gallery</strong></td><td>Use a curated configuration and customize it for your workload.</td><td><a href="https://docs.kinesis.network/getting-started/running-llms-with-kinesis-network/creating-apps-with-app-gallery.md">Deploy from the App Gallery</a></td></tr><tr><td><strong>Your image or repository</strong></td><td>Configure a container image or build from GitHub with the app wizard.</td><td><a href="https://docs.kinesis.network/getting-started/running-llms-with-kinesis-network/creating-an-app-from-scratch.md">Create a custom app</a></td></tr><tr><td><strong>Automation</strong></td><td>Create the project and app from scripts or an MCP client.</td><td><a href="https://docs.kinesis.network/api.md">REST API</a></td></tr></tbody></table>

{% stepper %}
{% step %}

## Create or choose a project

Open the [portal](https://portal.kinesis.network), select the organization from the account menu and open **Projects**. Admins and Developers can create projects; apps belong to that organization. See [Create a project](https://docs.kinesis.network/getting-started/running-llms-with-kinesis-network/creating-a-project.md).
{% endstep %}

{% step %}

## Configure the app

Choose **Create App** and work through **Source**, **Runtime**, **Network**, **Execution** and **Resources**. Review environment variables, the container port and the compute requirements before launching.

For a model server, check the model's GPU memory needs and any registry or model-download credentials. For a repository, confirm the branch, build context and Dockerfile.
{% endstep %}

{% step %}

## Choose compute and launch

Use [serverless CPU capacity or a grid](https://docs.kinesis.network/getting-started/running-llms-with-kinesis-network/understanding-compute-sources.md). Select an accessible grid and check capacity and the app creator’s quotas. If the organization has disabled serverless capacity for Developers, use a grid or ask an admin.

GPU workloads require a grid; serverless GPUs are currently paused. Small supported LLM templates can offer a CPU trial in the gallery.

Launching starts deployment and can consume the organization’s credits. A repository first goes through a build; a dedicated grid may need to acquire machines before the app starts.
{% endstep %}

{% step %}

## Verify the endpoint

Open the app's status, logs and metrics. Use the endpoint shown by Kinesis once it is ready. The container must listen on the configured port and bind to `0.0.0.0` to accept incoming traffic.

If deployment stalls, follow [Monitor and troubleshoot](https://docs.kinesis.network/getting-started/running-llms-with-kinesis-network/monitoring-apps.md).
{% endstep %}
{% endstepper %}


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.kinesis.network/getting-started/running-llms-with-kinesis-network.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
