> ## Documentation Index
> Fetch the complete documentation index at: https://docs.levelrail.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Self-host Crawl4AI with Docker

> An open source web crawler API that turns pages into clean Markdown and structured data for LLM pipelines, with a built-in playground and MCP endpoint. API calls need the generated token as a Bearer header.

An open source web crawler API that turns pages into clean Markdown and structured data for LLM pipelines, with a built-in playground and MCP endpoint. API calls need the generated token as a Bearer header.

This page describes the Levelrail template for Crawl4AI (AI). It deploys the services below as one Docker Compose app on your own server. Project site: [https://docs.crawl4ai.com/core/docker-deployment/](https://docs.crawl4ai.com/core/docker-deployment/).

Recommended memory: about 2048 MiB.

## Services, ports and volumes

| Service | Image | Container ports | Volumes |
| - | - | - | - |
| `crawl4ai` | `unclecode/crawl4ai:0.9.5` | 11235 | none |

## Environment variables

| Service | Variable | Value |
| - | - | - |
| `crawl4ai` | `CRAWL4AI_API_TOKEN` | Generated at deploy |

Passwords and keys marked as generated are created for you when the app is deployed and stored as secrets. Values are not shown here.

## Security and requirements

Level: **Elevated access**.

What this template needs:

* Changes container security options (`crawl4ai`): no-new-privileges:true.
* Passwords and keys are generated at deploy time (`crawl4ai`): CRAWL4AI\_API\_TOKEN.

What Levelrail adds around it:

* Automatic HTTPS and an ingress shield in front of every domain.
* Secrets are generated, stored encrypted and masked in logs and the UI.
* Deploys are gated on the health check before traffic switches.
* One-step rollback to the previous revision.
* Exposure report shows what is reachable from outside.
* Host firewall rules managed for published ports.

## Deploy Crawl4AI with Levelrail

In the dashboard, open **Apps**, choose **New app**, then **Browse templates**, and select Crawl4AI. Review the Compose body and deploy.

With the CLI:

```bash theme={"dark"}
levelrail-cli templates deploy crawl4ai --name my-crawl4ai
```

See the [service template catalog](https://docs.levelrail.com/templates-and-registry.md) for how templates work, and [Getting started](https://docs.levelrail.com/getting-started.md) if you have not installed Levelrail yet.

## More AI templates

* [AnythingLLM](https://docs.levelrail.com/self-host/anythingllm.md)
* [ComfyUI](https://docs.levelrail.com/self-host/comfyui.md)
* [Flowise](https://docs.levelrail.com/self-host/flowise.md)
* [Flowise (Postgres + Qdrant)](https://docs.levelrail.com/self-host/flowise-postgres.md)
* [Jupyter GPU Notebook](https://docs.levelrail.com/self-host/jupyter-gpu.md)

All templates are listed in the [self-host gallery](https://docs.levelrail.com/self-host.md).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.