Open WebUI VPS HostingA Private AI Chat Interface
Open WebUI is a self-hosted chat interface for AI models, with accounts, chat history and model switching. We install it with Ollama on a hardened VPS, behind NGINX with HTTPS on your domain, so you and your team chat with small open models on your own server.
Full root & SSH NVMe storage Daily backups Anti-DDoS 99.9% uptime SLA 11 locations
-
A familiar chat interface
Conversations, history and model switching in the browser.
-
Reserved vCores and RAM
Memory for the models behind the chat.
-
Your data on your server
Chats are stored on the VPS you control.
-
Daily backups
Automatic backup of the previous 24 hours.
Why Self-Host Open WebUI on a VPS
A shared chat tool puts every conversation on someone else's platform. Open WebUI runs on your server with the models you choose.
-
Conversations stay on your server
Chat history lives in the Open WebUI data volume on your VPS.
-
Accounts for your team
The first account you create becomes the administrator; you decide who else can sign up.
-
Switch between models
Use any model Ollama has downloaded, from the same screen.
-
Use from any browser
Reach it on your own domain over HTTPS, from desktop or phone.
How Open WebUI Is Set Up
Open WebUI in a container, Ollama as the model runtime and NGINX in front.
Request from a browser or app (HTTPS)
-
Reverse proxy
NGINX
HTTPS on your domain, with WebSocket support.
-
Application
Open WebUI (Docker container)
The chat interface, accounts and chat history.
-
Model runtime
Ollama
Runs the models on the CPU; API on localhost.
-
Data
Docker volume on NVMe
Chat history, settings and uploaded files.
Worth knowing
- The VPS plans have no GPU, so models run on the CPU: slower than on a GPU, and best with small models.
- Switch off open sign-up or require approval once your own accounts exist.
- Open WebUI can also connect to hosted AI services if you add your own API keys; that sends prompts to them.
- Back up the Open WebUI data volume.
What You Can Run
-
A private team chat assistant
One interface for several people on your own server.
-
Document questions
Upload files and ask about them, within what a small model can handle.
-
Prompt libraries
Saved prompts your team reuses.
-
Model comparison
Ask the same question of two small models side by side.
-
A front end for hosted APIs
Add your own API keys and use hosted models from the same screen.
-
A demo for clients
Show an AI chat on your own domain.
VPS Plans for Open WebUI
Open WebUI itself is light; the models need the memory. VPS-2 (8 GB RAM) is a sensible start, VPS-4 (24 GB RAM) gives room for larger models.
VPS-1
Small websites, APIs, bots and development servers.
- 2 vCores
- 4 GB RAM
- 40 GB NVMe
- 500 Mbps
- Full root and SSH access
- Free initial stack installation
- Server hardening and firewall setup
- Daily backup of the previous 24 hours
- Unlimited traffic *
- Anti-DDoS protection
- Dedicated IPv4 and IPv6
- KVM virtualisation
VPS-2
Production apps, WordPress and online stores.
- 4 vCores
- 8 GB RAM
- 75 GB NVMe
- 1 Gbps
- Full root and SSH access
- Free initial stack installation
- Server hardening and firewall setup
- Daily backup of the previous 24 hours
- Unlimited traffic *
- Anti-DDoS protection
- Dedicated IPv4 and IPv6
- KVM virtualisation
VPS-3
Busy stores, SaaS products and several projects.
- 6 vCores
- 12 GB RAM
- 100 GB NVMe
- 2 Gbps
- Full root and SSH access
- Free initial stack installation
- Server hardening and firewall setup
- Daily backup of the previous 24 hours
- Unlimited traffic *
- Anti-DDoS protection
- Dedicated IPv4 and IPv6
- KVM virtualisation
VPS-4
High-traffic apps, large databases and agencies.
- 8 vCores
- 24 GB RAM
- 200 GB NVMe
- 3 Gbps
- Full root and SSH access
- Free initial stack installation
- Server hardening and firewall setup
- Daily backup of the previous 24 hours
- Unlimited traffic *
- Anti-DDoS protection
- Dedicated IPv4 and IPv6
- KVM virtualisation
* Unlimited traffic in Europe and North America. In Mumbai, Singapore and Sydney a monthly allowance applies (VPS-1 500 GB, VPS-2/VPS-3 1 TB, VPS-4 3 TB), then speed is limited to 10 Mbps until the next month.
Prices exclude 18% GST, which is added to invoices for customers in India.
Which Plan for Open WebUI and Ollama
Plan for the model first. The interface adds little on top. There is no GPU, so replies are slow with larger models.
| Workload | Start with | Why |
|---|---|---|
| Trying it out with a tiny model | VPS-1 2 vCores · 4 GB RAM | 4 GB RAM; for tests only. |
| A few users, one small model | VPS-2 4 vCores · 8 GB RAM | 8 GB RAM and 75 GB NVMe. |
| More users, or a larger context | VPS-3 6 vCores · 12 GB RAM | 12 GB RAM and 6 vCores. |
| Larger models and headroom | VPS-4 8 vCores · 24 GB RAM | 24 GB RAM and 8 vCores; expect slower replies from big models. |
A starting point, not a limit: every plan upgrades in place, keeping your data, IP address and configuration.
Hosted Chat Service or Open WebUI on a VPS?
A hosted service gives you large models with no server work. Open WebUI keeps chats on your own server with smaller models.
| Feature | Hosted AI chat service | Open WebUI VPS |
|---|---|---|
| Pricing | Per user, per month | Flat server cost |
| Where chats are stored | The provider's servers | Your server |
| Models | The provider's models | Open models you pull, or hosted APIs you connect |
| Users and sign-up | Provider's accounts | Your own accounts and rules |
| Server administration | Handled by the provider | Yours, after our free setup |
| See Plans |
Looking After Your Open WebUI Server
Everyday tasks after handover.
-
Check the containers
Is Open WebUI running?
-
Read the logs
Useful when a model does not respond.
-
Download a model
Pull it with Ollama, then select it in the interface.
-
Update Open WebUI
Pull the new image and recreate the container.
-
Back up the data volume
Chats and settings.
# 1. Check the containers
sudo docker ps
# 2. Read the logs
sudo docker logs -f open-webui
# 3. Download a model
ollama pull llama3.2:3b
# 4. Update Open WebUI
sudo docker pull ghcr.io/open-webui/open-webui:main
# 5. Back up the data volume
sudo docker run --rm -v open-webui:/data -v ~/backups:/backup alpine tar czf /backup/open-webui-$(date +%F).tar.gz -C /data .
Example commands; adjust names, paths and versions to your project. Deploying and maintaining your application is yours to do (or ask us for a quote).
Installed and Secured Before You Log In
The VPS is unmanaged: after handover the server is yours to run. Before that, our engineers do the first setup once, free, so you start from a hardened server with Open WebUI in place.
-
Choose a plan and location
Pick the resources you need and the datacentre closest to your users.
-
Tell us your Open WebUI setup
Versions, database and domain: at order or right after.
-
We install and secure it
Server hardened, Open WebUI installed and tested, HTTPS on your domain.
-
You take over with root
SSH access to a working server, ready for your code and data.
Your Open WebUI setup
- Docker, Ollama and Open WebUI installed
- NGINX reverse proxy with WebSockets and HTTPS on your domain
- The first account left for you to create: it becomes the administrator
- No models downloaded: you choose them and read their licences
Yours to run after handover
- Ongoing server administration
- Application maintenance and updates
- Debugging your code
- Migrating existing sites or data
Not included in the free setup, but we can quote for it. No control panel by default: CloudPanel, HestiaCP or Virtualmin on request at no cost; cPanel and Plesk need their own licence.
Platform Specs and Locations
The same KVM platform on every plan; only the CPU, RAM, storage and port speed change.
| Virtualisation | KVM with reserved vCores and RAM |
|---|---|
| Storage | NVMe SSD on every plan |
| Network | Dedicated IPv4 and IPv6, 500 Mbps to 3 Gbps per plan |
| Operating systems | Ubuntu 26.04, 24.04 and 22.04 LTS · Debian 13, 12 and 11 · AlmaLinux · Rocky Linux · Fedora · FreeBSD |
| Access | Full root over SSH, key-based login |
| Backups | Automatic daily backup of the previous 24 hours; snapshots and longer retention on request |
| Protection | Always-on anti-DDoS mitigation |
| Availability | 99.9% uptime SLA |
Secured before we hand it over
- Non-root sudo user created for daily work
- SSH key login, password login for root disabled
- Firewall (UFW) open only for the ports you use
- Fail2ban blocking repeated login attempts
- Automatic security updates enabled
- Free Let's Encrypt SSL on your domain
- Timezone, swap and hostname configured
Asia-Pacific
- Mumbai
- Singapore
- Sydney
Europe
- London
- Limburg
- Roubaix
- Gravelines
- Strasbourg
- Milan
- Warsaw
North America
- Beauharnois
Availability per location changes with demand; we confirm your location before setup. In Mumbai, Singapore and Sydney each plan includes a monthly traffic allowance (VPS-1 500 GB, VPS-2 and VPS-3 1 TB, VPS-4 3 TB); beyond it, speed is limited to 10 Mbps until the next month.
Who an Open WebUI VPS Suits
-
Small teams that want private AI chat
One interface on your own server.
-
Developers evaluating open models
A friendly way to compare small models.
-
Agencies
A demo AI assistant on a client-facing domain.
Security and Performance for Open WebUI
Security
- Create the administrator account straight after setup, then restrict sign-up.
- Keep Ollama on localhost; only NGINX should face the internet.
- Keep Open WebUI and Docker updated.
- Remember that adding a hosted API key sends prompts to that provider.
Performance
- Use small, quantised models; larger ones answer slowly on CPU.
- Keep one model loaded to avoid reload delays.
- Keep free RAM for the model and free disk for chat history.
- Keep the NGINX WebSocket settings so replies stream.
Questions Before You Deploy
Not covered here? Ask an engineer before you order.
Run a Private AI Chat on Your Own Server
Choose a plan and we hand over Open WebUI with Ollama and HTTPS on your domain.