Plans

LibreChat VPS Plans Coming Soon

We are preparing VPS plans with LibreChat VPS pre-installed. Below are the resources the application needs to run smoothly.
Minimum
  • Processor 2 vCPU
  • Memory (RAM) 2 GB
  • NVMe storage 30 GB

Together with MongoDB and Meilisearch; for use with cloud APIs.

Recommended
  • Processor 2 vCPU
  • Memory (RAM) 4 GB
  • NVMe storage 50 GB

For document uploads and several concurrent users.

Get notified when plans launch

Contact our team to learn more about LibreChat VPS plans or to plan the right setup for your needs today.

Contact Us Browse Linux VPS plans
Use Cases

What Can You Do with LibreChat?

Bring all the AI models your team uses together at one address, under your control.

Every model in one place

Use models from OpenAI, Anthropic, Google and others in one interface, and switch models mid-conversation.

Team accounts

Create accounts for your team, with email, OAuth or LDAP sign-in and usage limits.

AI agents

Build agents equipped with files, web search and MCP tools, and share them with your team.

Conversation branching

Branch a conversation in different directions and compare alternative answers.

Search your history

Search quickly across your entire chat history and find earlier answers easily.

Work with files

Upload documents, ask questions about them and request summaries and analysis.

Why TRVDS for LibreChat VPS?

Your application runs in our data center in Bursa, Turkey, on resources reserved for you alone.

Pre-installed

The application is installed automatically after your server is created. No need to deal with Docker or dependencies.

Dedicated resources

Intel Xeon Gold processors, DDR4 RAM and NVMe storage. CPU and memory are not shared with other customers.

DDoS protection and unlimited traffic

DDoS protection with 40 Gbps capacity and unlimited traffic are included in every VPS plan.

Full control

With root access you can update the application, add a domain and SSL, and install other services alongside it.

What Is LibreChat?

LibreChat is an open-source chat application that brings models from providers such as OpenAI, Anthropic, Google, OpenRouter and Ollama together in one ChatGPT-style interface. You can switch models within a conversation, branch conversations and search your chat history.

You can build AI agents and connect them to files, web search and external tools through MCP (Model Context Protocol). You can also upload files and ask questions about documents.

On Your Own Server for Teams

LibreChat is multi-user: people can sign in with email or methods such as OAuth and LDAP. Instead of per-seat subscriptions, you can give your whole team one interface with pay-as-you-go APIs and manage usage limits.

Chat history, user accounts and uploaded files are stored on your own server. When you use a cloud model, only the current request is sent to the provider. Because the server is in Turkey, your records stay in the country.

Licensing and Resources

LibreChat is MIT licensed and free, including for commercial use. The interface does not need a graphics card; models run through the providers’ APIs.

LibreChat runs together with MongoDB, Meilisearch for search and additional services for document features. We therefore recommend 2 vCPU and 2 GB RAM as the minimum, and 4 GB RAM for document uploads and several concurrent users.

FAQ

Frequently Asked Questions About LibreChat VPS

Check the most frequently asked questions and find answers instantly.

Yes. LibreChat is MIT licensed and free on your own server, including for commercial use. Cloud model usage is billed by the provider.

It works with models from OpenAI, Anthropic, Google, Azure OpenAI, OpenRouter and other OpenAI-compatible providers, and with local model servers such as Ollama.

Both are self-hosted AI chat interfaces. LibreChat focuses on bringing many cloud providers together in one interface and on agents, while Open WebUI is stronger with local models through Ollama.

Yes. LibreChat is multi-user; people can sign in with email, OAuth or LDAP, and you can set usage limits.

Together with MongoDB and Meilisearch it needs at least 2 vCPU and 2 GB RAM. For document features and several concurrent users, we recommend 4 GB RAM.

Chat history, user accounts and uploaded files are stored in the database on your own server.