> For the complete documentation index, see [llms.txt](https://docs.biodock.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.biodock.ai/projects-and-models/public-ai-models.md).

# Publishing and public models

*What you'll get: how to run a model someone else published, and how to publish your own model so anyone on Biodock can run it.*

## Using public models

{% hint style="info" %}
Using public models is available on request. If you don't see **Public models** in the sidebar, contact [Biodock support](https://docs.biodock.ai/about/contact-us.md) to turn it on. Publishing your own model needs no request; see below.
{% endhint %}

To add a public model to your account:

1. Click **Public models** in the sidebar.
2. Search for a model, or filter the list with **All models**, **Available now** and **On-demand**. Each model shows its **Input requirements** (what images it expects) and its **Output** (what it finds).
3. Under **Available now**, click **Add** next to the model you want.
4. Start a new analysis: the model is listed under **Biodock models** in the **Pipeline** step. See [Running an analysis](https://docs.biodock.ai/analysis-and-results/running-an-analysis.md).

To stop using a model, click **Remove** next to it on the **Public models** page.

Some accounts also see **Try demo**, which runs the model on one image you pick.

### On-demand models

The page also lists **On-demand models**. These are models Biodock has not built yet, so they can't be added or run. Click **Request** and pick at least one of your images to tell the Biodock team you need one. A request is not a commitment to build the model.

## Publishing your model

Publishing lets anyone on Biodock run your model on their own images. They see the model name and your descriptions only. They can't see your project, its images, its labels or its training data.

Only active versions can be published. In your personal account, the project owner publishes. In a [workspace](https://docs.biodock.ai/workspaces/workspaces/members-and-roles.md), only workspace owners and admins can publish or unpublish the workspace's models.

1. Open your project and go to the **Active models** tab.
2. Click **Manage** on the version you want to share, and choose **Publish to the community**.
3. In the **Publish Version … to the community** window, enter a **Model name**, the **Input** (what the model expects to receive) and the **Output** (what it finds in those images). All three are required. Good descriptions are how others decide whether your model fits their images.
4. Click **Publish**.

The version now carries a **Public** tag.

A model you have not published runs only in the account where you trained it: a workspace model runs in that workspace, and a personal model in your personal account.

### Unpublishing

1. Click **Manage** on the published version and choose **Unpublish from the community**.
2. In the **Unpublish Version …?** window, click **Unpublish**.

Nobody new can add the model after that. You can publish it again later.


---

# 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.biodock.ai/projects-and-models/public-ai-models.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.
