AI and agents · Rio de Janeiro or São Paulo

VPS with Open WebUI Installed

Open WebUI is a ChatGPT-style AI chat that runs on your own server. Connect an AI provider's API key and your team can chat, attach files and keep the history under your control. Here it arrives already installed, with HTTPS.

Debian 13 with Docker
HTTPS and admin ready
Rio de Janeiro or São Paulo, Brazil
Public sign-up closed

open-webui.yourdomain.com

Chat screen in Portuguese, ready to choose the model…

Admin panel > Connections: where you enter the key…

Chat screen in Portuguese, ready to choose the model…3 screens

Plans

VPS plans to host Open WebUI

The AI runs on the provider you connect, so the VPS only handles the interface, user accounts and documents. The app needs at least 1536 MB of free memory, and the recommended plan is Basic.

Location

Selected

Recommended

Basic

US$ 11.95/mo

2 vCore CPU
2 GB Memory
NVME 40 GB Disk
Unlimited Traffic

Ask on WhatsApp

Plus

US$ 16.95/mo

2 vCore CPU
4 GB Memory
NVME 80 GB Disk
Unlimited Traffic

Ask on WhatsApp

Pro

US$ 21.95/mo

4 vCore CPU
6 GB Memory
NVME 120 GB Disk
Unlimited Traffic

Ask on WhatsApp

Turbo

US$ 35.95/mo

4 vCore CPU
12 GB Memory
NVME 160 GB Disk
Unlimited Traffic

Ask on WhatsApp

Billed monthly in US dollars, with the app installed. Rio de Janeiro or São Paulo, same price. Plans start at the smallest size where the app runs well. Need more? Upgrade from the client area, without reinstalling.

Where the server lives

Open WebUI in Rio de Janeiro

With Rio de Janeiro selected, your VPS with Open WebUI runs in Mega's original data center, on our own network with a presence at the Rio internet exchange (IX.br) and redundant transit. It is the lowest latency for users in Rio, Espírito Santo and Minas Gerais, and our support team works in the same city as the server.

Measured latency, not a promisemeasured 18 minutes ago

Rio de Janeiro to

Vivo11.4ms

Claro19.5ms

TIM20.2ms

Oi11.1ms

Algar4.5ms

São Paulo to

Vivo15.0ms

Claro8.6ms

TIM23.7ms

Oi15.2ms

Algar7.0ms

Ping from real customer connections on each carrier to our data centers in Rio and São Paulo, measured every hour by independent probes (Globalping). Algar: measured from our edge, where we connect to it directly.

What is Open WebUI?

Open WebUI is a self-hosted AI chat platform. The interface looks like ChatGPT, but conversations, uploaded files and user accounts are stored on your VPS.

Answers come from the AI provider you choose. In Settings > Connections, you enter the key from OpenAI or any service with a compatible API, such as Gemini, OpenRouter or Groq, and set which models your team can use.

During installation, the administrator account is created and public sign-up is closed. The Ollama integration, used for local models, is turned off, because those models need far more memory and processing power than a standard VPS provides.

Source: Official Open WebUI repository on GitHub

What you get on delivery

Open WebUI 0.11.4 in a Docker container, with automatic restart
Debian 13 as the operating system, with root access over SSH
Dedicated HTTPS address with a Let's Encrypt certificate
Administrator account created and public sign-up closed
Passwords and keys generated at installation, just for you
Access details sent by email and WhatsApp
VPS panel in the client area: restart, reinstall, change password and console

What you can do with Open WebUI

Company AI chat

Your whole team uses AI in one place, with individual accounts and no need for a separate subscription per person.

Questions about documents

Upload PDFs and text files and ask about what they contain.

More than one model

Switch models in each conversation and compare answers side by side.

Custom assistants

Create models with fixed instructions, such as a writer in your brand's tone or a first-line support agent.

Permissions by group

Decide which users and groups can access each model.

History you keep

Conversations stay on your server, not in each employee's personal account.

Open WebUI up close

Chat screen in Portuguese, ready to pick a model as soon as the AI provider is connected (example).

Admin panel under Connections, where the OpenAI key or a compatible provider's key goes (example).

Images captured by Mega Dedicados on a test installation, with no customer data.

What comes configured on your VPS

Debian 13 with Docker

Operating system and container environment ready, with Open WebUI 0.11.4 running.

HTTPS address

A dedicated domain for the app, with a Let's Encrypt certificate already issued.

Administrator created

The initial account exists from delivery, with a password generated just for you.

Sign-up closed

Outsiders cannot open accounts. Only the administrator adds users.

Portuguese interface

The default language comes set to Brazilian Portuguese.

Automatic restart

If the server reboots, the Open WebUI container starts on its own.

How to order

1
Choose the plan and the city
Select the plan with Open WebUI and pick whether the VPS is in Rio de Janeiro or São Paulo, Brazil. The price is the same.
2
Pay
Pay by Pix, card or boleto, on a monthly, semiannual or annual cycle. No lock-in contract.
3
Wait for the installation
The VPS is created with Debian 13, Docker and Open WebUI, already with HTTPS and an administrator.
4
Log in and connect the AI
Receive the address and password by email and WhatsApp, open the app's admin panel and paste your provider's key.

Which plan to choose for Open WebUI

Open WebUI idle already uses about 1.1 GB and needs at least 1536 MB free, so Basic, the recommended plan, covers small teams well. Move up as users and uploaded documents grow, since the AI runs on the provider's side.

Plan	Best for
Basic 2 vCore · 2 GB	The recommended plan: fits a small team using the chat daily, with few documents and headroom above the minimum.
Plus 2 vCore · 4 GB	Suits larger teams or heavier use, with several simultaneous users, more attached files and a growing history, with more breathing room.
Pro 4 vCore · 6 GB	For those working with many uploaded documents and several active users at the same time, without memory or processing strain.
Turbo 4 vCore · 12 GB	Built for heavy, continuous use, with a large team, plenty of uploaded content and room to grow without changing plans.

Frequently asked questions

Open WebUI hosting FAQ

How much does Open WebUI hosting cost?

A VPS with the app installed starts at the Basic plan, at US$ 11.95 per month, which is the recommended one. AI usage is separate and billed by the provider you connect.

Do I need an AI API key to use Open WebUI?

Yes. Open WebUI is only the interface, and the answers come from the provider. Enter your OpenAI key or a compatible service's key in Settings > Connections, in the admin panel.

Can I run local models with Open WebUI on a VPS?

The Ollama connection is turned off. Local models use a lot of memory and usually need a GPU, which is beyond what a standard VPS offers.

Can anyone sign up on my self-hosted Open WebUI?

No. Public sign-up is delivered closed, and only the administrator creates new users.

How do I update Open WebUI on my VPS?

The delivered version is 0.11.4 and stays pinned, so nothing changes without warning. When you want to update, log in over SSH as root and make the switch after testing.

Can I reinstall my Open WebUI VPS from scratch?

Yes. In the VPS panel, in the client area, there is an option to reinstall the server. Current data is erased and you receive new access details.

Can I install other apps on the same VPS?

Yes. Each app gets its own address, as long as they all fit in the plan's memory. Open WebUI alone already takes about 1.1 GB.

How does support work?

Support is available 24 hours a day, in Portuguese, by WhatsApp, ticket and phone, for everything involving the server. Using the app itself is covered by the Open WebUI project's documentation.

Updated on October 19, 2026