Perimattic
ManageStacks · AI & ML

Managed LobeChat Hosting — production-ready from $11 a month

Open-source chat framework for running a private ChatGPT-style app with many LLM providers. Deployed on your own dedicated instance in AWS, Azure, or GCP, kept patched, backed up, and monitored by ManageStacks — standard LobeChat, no lock-in.

LobeChat on ManageStacks is an open-source chat interface for large language models, deployed to your own AWS, Azure, or GCP region — flat per-app pricing from $11 a month ($25 on the Standard production plan). Teams get a private ChatGPT-style workspace that connects to several model providers, replacing per-seat tools like ChatGPT Team or Claude Team.

Daily backups includedAWS · Azure · GCPData export any time24×7 SRE available
LobeChat logo
LobeChat
Open-source chat framework for running a private ChatGPT-style app with many LLM providers
The application

What does LobeChat do, and why do teams deploy it?

LobeChat is an open-source chatbot framework written in TypeScript. It gives you a polished chat interface that you point at the model providers of your choice, including hosted APIs and locally served models, so one deployment can front several LLMs. You bring your own API keys, which means usage is billed by the model vendor instead of per seat. The interface supports conversation management, assistant presets, and a plugin system for extending what the model can do. Because it is self-hosted, conversations and settings stay in your own infrastructure rather than a third-party chat product.

  • Single chat interface across multiple LLM providers
  • Support for locally hosted models alongside hosted APIs
  • Reusable assistant presets with custom system prompts
  • Plugin system that extends models with external tools
  • Conversation history organised into topics and sessions
  • Multimodal chat with image input on capable models
Neural network visualization representing machine learning inference
AI & ML

Open-source chat framework for running a private ChatGPT-style app with many LLM providers

Open-source alternative

LobeChat as a self-hosted alternative to ChatGPT Team and Claude Team

Instead of paying per-seat fees to a SaaS vendor, teams self-host LobeChat to keep full control of their data and infrastructure. ManageStacks removes the operational overhead — you get the cost and privacy benefits of open source with the reliability of a managed platform.

Replaces ChatGPT TeamReplaces Claude Team
Pricing

What does managed LobeChat hosting cost?

Flat per-app pricing, in your chosen AWS, Azure, or GCP region. No per-user pricing — a busy deployment costs the same as a quiet one.

Starter

$11/app/mo

Staging and internal tools. Dedicated instance, TLS, daily backups, managed upgrades.

Standard

$25/app/mo

Production workloads. Adds monitoring, staging environment, region choice, priority support.

Business

$45/app/mo

High-traffic and compliance workloads. Adds a high-availability replica and same-day support.

24×7 SRE retainer

$499/mo

Round-the-clock on-call across every hosted application, for teams that need a pager answered at 3am.

The honest answer

When is self-hosting LobeChat the right answer instead?

“Managed hosting is not always the correct call.”

Self-host when a platform team already runs the infrastructure and on-call rotation to operate LobeChat at genuinely low marginal cost. Self-host when compliance requires an air-gapped or on-premises deployment that no hosted option can satisfy. And self-host when the deployment depends on heavy customisation with a fast internal build-deploy loop, because an internal release process will beat any managed change process.

For everyone else — teams whose engineers have better things to do than shepherd upgrades — managed hosting is cheaper than the hours it replaces.

Infrastructure

Which cloud should LobeChat run on — AWS, Azure or GCP?

For most workloads, the choice of cloud matters less than proximity: run LobeChat in the same cloud and region as the applications and data it talks to, because every request between them adds a round trip. The underlying compute performs equivalently across AWS, Azure, and GCP.

In practice, an existing cloud footprint decides it. All plans support all three clouds, and moving regions later is a scheduled migration, not a rebuild.

AWS logo
AWS

Deepest managed-service catalog, default when there's no existing footprint

Azure logo
Azure

Best fit for teams already on Microsoft 365 or Entra ID

GCP logo
GCP

Strongest for data/analytics-adjacent workloads

GPU compute hardware used for AI model inference
Multi-cloud

Every plan supports AWS, Azure, and GCP — region choice included.

FAQ

Common questions about LobeChat on ManageStacks

What is LobeChat on ManageStacks?

It is a private, self-hosted chat front end for large language models, run in your own cloud account. ManageStacks provisions the stack, SSL, and backups, so your team can start chatting with the models you configure.

How does LobeChat compare to ChatGPT Team?

ChatGPT Team is a per-seat SaaS limited to one vendor's models. LobeChat is self-hosted and can connect to several providers using your own API keys, so you pay the model vendors directly and keep conversation data in your environment.

Can LobeChat use more than one model provider?

Yes. It is designed to work with multiple providers and with locally served models, and you can switch between them per conversation or assistant. Which providers are available depends on the version you run and the keys you supply.

Do I keep my chat data if I leave?

Yes. The deployment runs in your own cloud account, so conversation data and settings are yours. You can export them from the app, and nothing about the hosting locks them to ManageStacks.

How are model API keys handled?

You supply your own provider keys in the configuration, and they stay inside your deployment rather than being shared with a third-party chat service. Rotating a key is a configuration change, and you control which team members can reach the instance.

Run LobeChat without carrying the pager

Subscribe through your AWS, Azure, or GCP marketplace. We handle provisioning, SSL, monitoring, backups, updates, and security. From $11/mo.