Deployment Options¶
Prerequisites
Overview¶
There are 4 main options for deploying with the LangGraph Platform:
-
Cloud SaaS(Beta): Available for Plus and Enterprise plans.
-
Self-Hosted Data Plane(Beta): Available for the Enterprise plan.
-
Self-Hosted Control Plane(Beta): Available for the Enterprise plan.
-
Standalone Container: Available for all plans.
Please see the LangGraph Platform Plans for more information on the different plans.
The guide below will explain the differences between the deployment options.
Cloud SaaS¶
The Cloud SaaS deployment option is a fully managed model for deployment where we manage the control plane and data plane in our cloud. This option provides a simple way to deploy and manage your LangGraph Servers.
Connect your GitHub repositories to the platform and deploy your LangGraph Servers from the Control Plane UI. The build process (i.e. CI/CD) is managed internally by the platform.
For more information, please see:
Self-Hosted Data Plane¶
The Self-Hosted Data Plane deployment option is a "hybrid" model for deployemnt where we manage the control plane in our cloud and you manage the data plane in your cloud. This option provides a way to securely manage your data plane infrastructure, while offloading control plane management to us.
Build a Docker image using the LangGraph CLI and deploy your LangGraph Server from the Control Plane UI.
Supported Compute Platforms: Kubernetes, Amazon ECS (coming soon!)
For more information, please see:
Self-Hosted Control Plane¶
The Self-Hosted Control Plane deployment option is a fully self-hosted model for deployment where you manage the control plane and data plane in your cloud. This option give you full control and responsibility of the control plane and data plane infrastructure.
Build a Docker image using the LangGraph CLI and deploy your LangGraph Server from the Control Plane UI.
Supported Compute Platforms: Kubernetes
For more information, please see:
Standalone Container¶
The Standalone Container deployment option is the least restrictive model for deployment. Deploy standalone instances of a LangGraph Server in your cloud.
Build a Docker image using the LangGraph CLI and deploy your LangGraph Server using the container deployment tooling of your choice. Images can be deployed to any compute platform.
For more information, please see:
Related¶
For more information, please see: