Free credit available Limited time
Available in console AI

Deploy Langflow
in one click.

A visual builder for LangChain agents, RAG pipelines and flows you can serve as an API, on a server we run for you.

Launch Langflow Browse all 44
Recommended from 8 GB RAM, from ~$0.03/hr (EU) 6 server locations No separate app fee

+$5.00 added at signup ยท exact template preserved ยท no card

What launches

The working stack,
preconfigured.

Choose the template and a project server. Selfhost.dev provisions the host and launches the application stack as one resource.

  • Langflow
  • Bundled PostgreSQL
  • Seeded superuser
  • Generated HTTPS endpoint

Good fit for

Use it where
it does real work.

  • 01 AI agents
  • 02 RAG pipelines
  • 03 Flows served as an API

From choice to app

A short path to
a usable deployment.

  1. 01

    Choose Langflow

    The page opens the exact console template. Pick a server size and one of six locations, then submit.

  2. 02

    Set access

    Sign in with the username (admin unless you choose another) and the password you set at deploy time. The superuser is created before the first boot with auto-login off, so the instance never starts open.

  3. 03

    Let it start

    The console tracks provisioning, gives the app a generated HTTPS address and shows host CPU and memory after launch.

  4. 04

    Make it yours

    Sign in with the login you set at deploy time. Add your model provider key, then build a flow from a template or a blank canvas.

Know before deploy

The operational details
that matter.

No model provider or API key is included, so add your own after you sign in. Anyone who signs up later on the Langflow page stays inactive until you activate them in its admin page. The bundled Postgres runs on the same project server and is not a separate managed database.

Capacity
Recommended from 8 GB RAM, from ~$0.03/hr (EU)
Topology
One project server
Initial address
Generated HTTPS URL
Protection
Optional whole-VM backup

Also in the catalog

Related one-click apps.

Browse all 44
Data

Qdrant

A vector database for embeddings, semantic search and RAG, on a server we run for you.
AI

LiteLLM

One OpenAI-compatible endpoint in front of every model provider, on a server we run for you.
AI

AnythingLLM

Chat over your own documents, on a server we run for you.

Frequently asked questions

Is Langflow available as a one-click template?
Yes. Langflow is one of 44 configurations in the console's global template chooser. The marketing page links directly to that configuration.
How much does it cost to run Langflow?
Recommended from 8 GB RAM, from ~$0.03/hr (EU). The app adds no separate fee. You pay only for the project server it runs on, by the hour against prepaid credits.
Does Langflow come with a model?
No. Langflow builds flows around the models you bring. Add the API key for your model provider in Langflow after you sign in.
Can Langflow serve a flow as an API?
Yes. A flow can be served as an API on the same HTTPS address as the editor, so your applications call the address the console shows.
How do I sign in to Langflow?
Sign in with the username (admin unless you choose another) and the password you set at deploy time. The superuser is created before the first boot with auto-login off, so the instance never starts open.
Can I use my own domain for Langflow?
The app first receives a generated HTTPS address. After it is running, add one customer-owned domain from the resource Settings screen and follow the DNS instructions.
What does Selfhost.dev manage for this deployment?
Selfhost.dev provisions and maintains the project server, starts the Langflow template and shows server CPU and memory metrics. The application and its data run on that single server; optional backups protect the whole project VM.

Exact template selected

Put Langflow
on your own server.

The app adds no separate fee. You pay only for the project server it runs on, by the hour against prepaid credits. The console keeps this template selected through sign-up and onboarding.

Launch Langflow