Purchase a Virtual Dedicated Server with Open WebUI Installation

Control your AI chat experience using Open WebUI, a self-hosted interface for large language models. Connect seamlessly to Ollama, OpenAI-compatible APIs, and other LLM providers while keeping your data entirely private and maintaining full control over the models you run.

It works with OpenAI-compatible APIs, Ollama, and many other LLM providers, so you choose which models to run.

This article explains how to purchase a Bluehost Virtual Dedicated Server (VDS) hosting plan and set up and manage your Open WebUI Assistant.

Why Choose Open WebUI?

Hosting Open WebUI on a VDS gives you full control over your AI environment with maximum data privacy. Unlike local setups, a VDS runs 24/7 in the cloud so your team can securely access models from any device at any time. You get dedicated hardware resources, ensuring fast and stable performance even during heavy multi-user workloads. Plus, it acts as a central hub, seamlessly connecting custom documents, local engines like Ollama, and external APIs like OpenAI into a single interface.

Uses of Open WebUI

You can use Open WebUI on a VDS for a variety of AI-powered projects, including:

• AI Chat Assistants — Set up chatbots for your team or customers that answer questions, handle support, and automate conversations.
• Knowledge Management Systems — Connect AI models to your company's documents so employees can search and get instant answers.
• Development and Testing — Try out prompts, workflows, and models in a safe space before you push anything live.
• Team Collaboration — Give everyone on your team access to AI tools through one shared interface.
• Content Generation — Write marketing copy, documentation, blog posts, and product descriptions faster.
• Research and Analysis — Summarize information, analyze data, and speed up research projects.
• Custom AI Applications — Build AI apps that connect to your APIs, databases, and business systems.

With your own VDS, you run every one of these projects on infrastructure you fully control.

System Requirements

Before deploying, ensure your server meets the following minimum hardware requirements. For a stable production deployment, we recommend using higher specifications than the minimum requirements.

How to Purchase a Virtual Dedicated Server with Open WebUI Installation

Open WebUI can be installed on a Bluehost Virtual Dedicated Server (VDS). You can choose to have Open WebUI installed during the initial VDS purchase or install it manually at a later time.

1. In your browser, go to https://www.bluehost.com.
2. Click Hosting in the top menu, then select Virtual Dedicated Server.

   
    

   You can also go to this link directly: https://www.bluehost.com/vds-hosting.

3. On the Virtual Dedicated Server Hosting page, click Explore Plans. You can also scroll down to the hosting plans section.

   
    

4. Choose a plan from either tab — Standard or High Performance — by clicking Choose Plan.

   
    

   Pricing is subject to change. Please visit https://www.bluehost.com/vds-hosting for the current introductory/sign-up offer for the Bluehost Virtual Dedicated Server hosting. For the most up-to-date renewal pricing, visit your Bluehost Portal's Renewal Center.
5. On the next page, configure your VDS hosting to meet your requirements. The configuration options are divided into the following sections:
   • Location: Select your data center in this section.

     
      

   • Hardware: This section shows your pre-selected plan. You can also switch to another Virtual Dedicated Server plan in this section.

     
      

   • Software:
     If the selected plan does not meet the app's minimum requirements, the app will be grayed out.
     1. Under the Application tab, click on Open WebUI.

        
         

        You can install only one application per purchase; the system will automatically select the best operating system for it.
     2. In the pop-up, click Confirm.

        
         

   • Support & Security: You can add Premium Support - Recurring, which provides priority access to expert assistance and faster response times.

     
      

   • Advanced Options:
     • Extra IP's: You can add IP addresses for an additional fee. Pricing changes based on how many IPs you add.
     • Hostname: Assign a custom hostname to identify your server. This is optional.

       
        

6. Select your billing term and review your selected items on the right pane, along with the summarized total cost.

   
    

7. Click Continue to checkout.
8. Do the following on the Checkout page:

   
   If you're new to Bluehost:

   1. Create your Bluehost account by using your email address or by connecting with your Google, Apple, or GitHub account — whichever you prefer!

      
       

   2. Select your preferred payment method: credit card, Google Pay, or PayPal. Enter your billing information.

      
       

   If you have an account with us, you will see your Bluehost login details when you are logged into your Bluehost Portal. If you are not logged in, please click the Log In link.

   
    

9. In the Shopping Cart, choose your billing term if you did not choose one on the previous page.

   
    

10. Add a Promo code if you have one, and then click Submit Payment to complete your purchase.

After completing the purchase, your VDS hosting will begin provisioning. You can access and manage your new VDS hosting in the Hosting tab of your Bluehost Portal.

How to Access Your Dashboard

Phase 1: Set Up and Secure Your VPS

1. Log in to your Bluehost Portal.
2. In the left-hand menu, click the Hosting tab.

   
    

3. Look for the server you want to manage then click the View Details to see more options.

   
    

4. Click the Reset Password.

   
    

5. In the pop-up window, type your new root password, then click Reset Password again to confirm and save the changes.

   
    

6. Connect to your VPS via SSH.
   Open your computer's terminal (or an SSH client like PuTTY) and run the following command to log into your server as the administrator, using your server's public IP address:
   Replace your_server_ip with your actual server IP address.

   ssh root@your_server_ip

   Follow the prompts and enter the new root password you created in the step above.
7. If you ever need to quickly review the system's deployment notes directly inside your server terminal, you can print out the original README file by running:
   Copy

   cat /root/README.md

Phase 2: Access and Configure Open WebUI

1. Find your server's public IP address (your server provider will show it).
2. Open your web browser and go to https://<your-server-ip>.
   Replace your_server_ip with your actual server IP address.
   (Example: http://12.3.456.789)
   Note on Security: Because it takes a moment to set up certificates, your browser might give you a "Your connection is not private" warning. If it does, click Advanced -> Proceed to IP (unsafe). This is normal for a brand-new server setup using self-signed certificates.
3. Click Get Started on the landing page. 

   Note: The very first person to create an account on this website gets full admin control over the system.

   
    

4. You will be prompted to create an account. Enter the required information to complete the sign-up process.

   
    

5. After creating your account, you will be redirected to your dashboard.

   
    

Choose Your AI Brains

By default, you can chat with the built-in llama3.2:1 b model. However, if you want to use incredibly powerful models like Claude (Anthropic), ChatGPT (OpenAI), or OpenRouter, follow the instructions in Step 3 of the README:

1. On the website, click the profile in the lower-left corner, then click Admin Panel.

   
    

2. Next, click Settings → Connections → OpenAI API.

   
    

3. Enter your API Base URL and your personal secret API Key from your provider.
   Create a developer account with your choice of AI provider to get your credentials:

   • OpenRouter: OpenRouter acts as a single gateway. One account gives you access to almost every model in existence (Anthropic Claude, OpenAI ChatGPT, Google Gemini, DeepSeek).
     • Access, openrouter.ai, then Sign up
     • Click Create Key, name it (eg, "Open WebUI VPS"), and click Create.
     • Copy the key immediately. You will not be shown it again. It looks like:sk-or-v1-xxxx...
     • Your Base URL: https://openrouter.ai/api/v1
   • OpenAI:
     • Go to platform.openai.com (the developer platform) and sign up.
     • In the left-hand sidebar, click API Keys.
     • Click Create new secret key, name it, and copy it immediately. It looks like: sk-proj-xxxx...
     • Your Base URL: https://api.openai.com/v1
4. Save it, and those models will now appear in your drop-down chat menu.

Useful Commands (If things go wrong)

The README lists several commands you can run directly in your server terminal (root@server-12345:~# ) to see what's happening under the hood:

• Check if the chat app is actively running:
  Copy

  systemctl status open-webui
• If the website freezes or you change a backend setting and want to force a refresh:
  Copy

  systemctl restart open-webui
• If you see an error on the screen and want to read the last 100 lines of system logs to troubleshoot:
  Copy

  journalctl -u open-webui -n 100

root@server-123456:~# cat /root/README.md
# Open WebUI

## Description

Open WebUI is a self-hosted, feature-rich web interface for interacting with large language models.

It supports OpenAI-compatible APIs, Ollama, and a wide range of LLM providers, giving you full control over your AI chat experience without sending data to third-party services.

This image ships Open WebUI on Ubuntu 24.04, served via Nginx with HTTPS support. On first boot, a secret key is generated and all services start automatically.


## Services

| Service   | Port    | Purpose                                        |
|-----------|---------|------------------------------------------------|
| Open WebUI| 8080    | Open WebUI application (internal only)         |
| Ollama    | 11434   | LLM inference backend (internal only)          |
| Nginx     | 80, 443 | TLS termination and reverse proxy to port 8080 |
| OpenSSH   | 22      | Remote access                                  |

Ports are protected using UFW. Port 8080 is not exposed externally.


## How-to-use

### 1. Access Open WebUI

Once the server has booted, open your browser and navigate to:

```
https://
```

### 2. Create your admin account

The first user to sign up automatically becomes the admin. Fill in your
name, email, and password on the sign-up page to create your account.

### 3. Connect an LLM backend

Open WebUI supports any OpenAI-compatible API. Go to:

```
Admin Area -> Settings -> Connections -> OpenAI API
```

Enter your API key and base URL for your chosen provider:

```
# OpenRouter
API Base URL : https://openrouter.ai/api/v1
API Key      : sk-or-...

# Together AI
API Base URL : https://api.together.xyz/v1
API Key      : ...

# Anthropic (via compatible proxy)
API Base URL : https://api.anthropic.com/v1
API Key      : sk-ant-...
```

### 4. Useful commands

```bash
systemctl status open-webui            # Open WebUI service status
systemctl status nginx                 # Nginx status
journalctl -u open-webui -n 100        # Recent Open WebUI logs
tail -f /var/log/open-webui/webui.log  # Live log stream
systemctl restart open-webui           # Restart Open WebUI
```

### 4. SSL / HTTPS certificate behavior

On first boot, a TLS certificate is automatically provisioned:

- A Let's Encrypt certificate is requested for the server's public IP.
- If Let's Encrypt is unavailable, a self-signed certificate is generated
  as a fallback.

Nginx terminates TLS on port 443 and proxies traffic to Open WebUI on
port 8080. The X-Forwarded-Proto: https header signals HTTPS to Open WebUI.

To manually request a Let's Encrypt certificate after deployment:

```bash
/opt/certbot/bin/certbot certonly --webroot --webroot-path /var/www/html   -m [email protected] --agree-tos --non-interactive --ip-address 

nginx -t && systemctl reload nginx
```


## Minimum Resources

| Resource | Minimum     | Recommended |
|----------|-------------|-------------|
| CPU      | 2 vCPUs     | 4 vCPUs     |
| RAM      | 2 GB        | 4 GB        |
| Disk     | 20 GB       | 40 GB       |

> The bundled **llama3.2:1b** model (~1.3 GB) can run on 2 GB RAM.
> To run larger models (7B+) add more RAM and disk accordingly.


## Image contents

This image installs and configures:

- Open WebUI (latest) installed at /opt/open-webui
- Ollama installed with **llama3.2:1b** model pre-pulled (~1.3 GB)
- Python 3 virtual environment at /opt/open-webui
- Nginx as a reverse proxy with HTTP and HTTPS support
- UFW firewall with ports 22, 80, and 443 open
- Log rotation at /etc/logrotate.d/openwebui
- This README at /root/README.md


## Security hardening

| Hardening       | Detail                                             |
|-----------------|----------------------------------------------------|
| UFW firewall    | Only ports 22, 80, 443 open. Default deny incoming |
| SSH             | Password authentication disabled                   |
| Open WebUI      | Bound to 127.0.0.1 only, not exposed externally    |
| Secret key      | Generated at first boot via openssl rand           |
| Credentials     | Stored in /root/.app_passwords (mode 0600)         |


## Configuration files reference

| File                                           | Purpose                          |
|------------------------------------------------|----------------------------------|
| /etc/systemd/system/open-webui.service         | Open WebUI systemd service       |
| /etc/default/open-webui                        | Open WebUI environment config    |
| /etc/nginx/sites-available/openwebui           | Nginx site config                |
| /root/.app_passwords                           | Generated credentials            |
| /var/log/open-webui/webui.log                  | Open WebUI application log       |
| /etc/logrotate.d/openwebui                     | Log rotation config              |


## Links

- Manage: [https://{server_ip}](https://{server_ip})
- Documentation: [https://docs.openwebui.com](https://docs.openwebui.com)
- Open WebUI GitHub: [https://github.com/open-webui/open-webui](https://github.com/open-webui/open-webui)