AIHostBox
Client area Deploy an app
All 57 applications
CategoriesAI assistants & chatLLM runtimesAgents & RAGGateways & LLM opsVector & dataAutomationSpeech, image & videoSearch & web agentsSupport & CXML platformMCP servers
SolutionsPrivate team chatUnlimited automationCompany knowledge AIAI gateway & observability
More PricingGuides ComparisonsToolsPrivate LLM hosting LicensingSecurity SupportClient area

LibreChat hosting

Multi-model chat with agents, plugins and conversation forking.

AI assistants & chatMITfrom $11.99/mo
In short

LibreChat hosting at AIHostBox means a dedicated, single-tenant LibreChat instance on our infrastructure: we install it, pin it to a reviewed release, put it behind TLS on your domain, back it up nightly and keep it patched. Plans start at $11.99 per month and the admin account, the data and any API keys are yours.

Multi-providerAgentsConversation forkingPresetsFile RAGMongoDB

LibreChat rebuilds the ChatGPT interface as open software and then keeps going: side-by-side model comparison, conversation branching, custom agents and endpoints, code interpreter support, presets you can share across a team, and file handling with RAG. It speaks to OpenAI, Anthropic, Google, Azure, AWS Bedrock, OpenRouter and any OpenAI-compatible local server, and it can hold several of them at once.

It is a heavier stack than a single-container chat UI — MongoDB, a search index and the API service — so we start it at 4 GB rather than sell you a tier that will disappoint. Backups cover the database as well as uploaded files.

LibreChat hosting plans

PlusRecommended minimum
4 GB RAM · 2 vCPU · NVMe
$11.99/mo
Order
ProTeams & heavier load
8 GB RAM · 3 vCPU · NVMe
$18.99/mo
Order

Every plan is a dedicated single-tenant instance with NVMe storage, nightly off-box backups, TLS and managed patching. Quarterly, semi-annual and annual terms are discounted at checkout. Model tokens are not included — you bring your own key.

How we run LibreChat

The official LibreChat compose layout: the API/web container on port 3080, MongoDB, Meilisearch for conversation search, and the RAG API backed by a pgvector Postgres database for file uploads.

What we configure for you

  • JWT_SECRET, JWT_REFRESH_SECRET, CREDS_KEY and CREDS_IV generated per instance
  • MEILI_MASTER_KEY set and search enabled so conversation history is searchable
  • librechat.yaml with your providers and any custom OpenAI-compatible endpoints
  • ALLOW_REGISTRATION and ALLOW_SOCIAL_LOGIN set to match how open you want sign-up
  • EMAIL_* SMTP settings for password resets and verification
  • OPENID_* single sign-on when you bring an identity provider

Which plan fits

Plus (4 GB) carries the five containers comfortably for an individual or a small team, with room for occasional document uploads. Pro (8 GB) is for a team sharing agents and presets daily, heavier file RAG and a larger MongoDB working set.

The honest limits

LibreChat runs no models itself, and file chat needs an embeddings provider for the RAG API (OpenAI by default); pointing it at a local CPU embedding model works but indexes large uploads slowly.

What people run LibreChat for

Power-user chat

Fork a conversation to try a different approach without losing the original thread.

Model bake-offs

Run the same prompt against two providers and keep the better answer.

Team presets

Publish reviewed system prompts so everyone starts from the same baseline.

Licence and version policy

ItemPosition
Upstream licenceMIT
Sold as managed hostingYes
TenancySingle tenant — one customer per instance
PatchingCritical advisories within 24 hours, high severity within 72

Our full position on licences, including the applications we decline to sell, is on the licensing page.

Reading on LibreChat

ComparisonOpenClaw alternativesGuide · Team chatPrivate ChatGPT for your team, on a server you control

Works well with LibreChat

LiteLLM logo

LiteLLM

One OpenAI-compatible endpoint in front of every model provider you use.

from $5.99/moDetails →Ollama logo

Ollama

Your private LLM server — pull a model, get an API, keep every token on your own box.

from $16.99/moDetails →LocalAI logo

LocalAI

A drop-in OpenAI replacement for text, images, audio and embeddings.

from $16.99/moDetails →

More AI assistants & chat we host

OpenClaw logo

OpenClaw

Your always-on personal AI assistant, running 24/7 on a server you control.

from $9.99/moDetails →Open WebUI logo

Open WebUI

A ChatGPT-style workspace for your team, pointed at any model you like.

from $5.99/moDetails →LobeChat logo

LobeChat

A fast, polished chat UI with a large plugin and assistant marketplace.

from $11.99/moDetails →SillyTavern logo

SillyTavern

The character-driven chat front-end, online wherever you are.

from $5.99/moDetails →
Questions

LibreChat hosting: your questions

How is this different from Open WebUI?
Open WebUI is the smoother general workspace; LibreChat goes deeper on multi-provider work — forking, side-by-side comparison and custom agent endpoints. Teams that argue about models tend to prefer LibreChat.
Does it support local models?
Yes, any OpenAI-compatible endpoint including Ollama, LocalAI and vLLM.
Can staff sign in with our identity provider?
Yes. LibreChat supports OpenID Connect through the OPENID_* settings (issuer, client ID and secret, callback URL), and can require a specific role from the token. We can switch off open sign-up with ALLOW_REGISTRATION=false so only people from your directory get in.
What exactly is in the backup?
The MongoDB database (users, conversations, presets, agents), uploaded files, and the pgvector database holding embeddings for file chat. The Meilisearch index is also copied, although LibreChat can rebuild it from MongoDB if it is ever lost.
Can I move my existing self-hosted LibreChat here?
Yes. Send us a mongodump plus your uploads folder and librechat.yaml. Keep your CREDS_KEY and CREDS_IV values: they encrypt the API keys users have saved, and with new values those stored keys can no longer be decrypted.
How do I add a custom endpoint such as OpenRouter or a local model server?
Custom endpoints live in librechat.yaml, the configuration file mounted into the API container. Tell us the base URL, model list and key and we add the endpoint; after a restart it appears in the model picker for every user.

Run LibreChat without running a server

A dedicated LibreChat instance, deployed and maintained by us. Month to month, cancel whenever.

Browse the catalogue Talk to a human