LangGraph Platform plans
for teams of any size

Developer
Get started with Self-Hosted Lite deployment.
‍
Designed for startups and hobbyists to build & experiment with dynamic AI agent experiences.
Includes up to 1M nodes executed
Key features:
Horizontally scalable task queues and servers
APIs for retrieving & updating state and conversational history
APIs for retrieving & updating long-term memory
Real-time streaming
Assistants API
Plus
Self-serve with Cloud SaaS deployment.
‍
Designed for teams looking to quickly deploy their agentic apps, accessible from anywhere.
Free (while in beta)  
First 10k traces included, starting at $0.50 per 1k base  traces thereafter.
Key features:
All features in Developer tier
Cron scheduling
(Coming soon) Auth to call LangGraph APIs
(Coming soon) Smart caching
(Coming soon) Publish/subscribe API for state changes
Enterprise
Deployed where you need it -- Bring Your Own Cloud, Self-Hosted Enterprise, or cloud SaaS options.
‍
Designed for teams with more security, deployment, and support needs.
Custom
Key features:
All features in Plus tier
Enterprise deployment options, including full self-hosted and hybrid
SLA for managed offerings
Team trainings
Shared Slack channel
Architectural guidance
Dedicated customer success engineer

LangSmith for Startups and Education

Seed stage startups and educational institutions, reach out for starter pricing and get shipping today.

Startups
Education

Compare plans

Developer
Plus
Enterprise
Features
APIs for retrieving and updating state and conversational history
APIs for retrieving and updating long-term memory
Horizontally scalable task queues and servers
Real-time streaming of outputs and intermediate steps
Assistants API (configurable templates for LangGraph apps)
Cron scheduling
LangGraph Studio for prototyping
Authentication & authorization to call the LangGraph APIs
Smart caching to reduce traffic to LLM API
Coming soon!
Coming soon!
Publish/subscribe API for state
Coming soon!
Coming soon!
Scheduling prioritization
Coming soon!
Coming soon!
Deployment
Self-Hosted Lite. Limited to 1M nodes executed. Logs traces to LangSmith by default.

Read the docs to get started.
Cloud SaaS with data residency in the US or EU.

Read the LangGraph Cloud docs to get started.
Three options:
‍
-  Cloud SaaS  with data residency in the US or EU.
‍
- Hybrid (SaaS control plane, self-hosted data plane). No data leaves your VPC. Provisioning and scaling managed as a service.

- Self-Hosted. No data leaves your VPC. Self-managed deployment.


Contact sales to get started.
‍
Support
SLA
Available for certain deployment types
Help with cognitive architecture design
Dedicated customer support
Procurement
Billing
Annual invoice
Signed contract

LangGraph Platform
Pricing FAQs

What is LangGraph Platform?

LangGraph Platform is a platform for deploying AI agents that can scale with production volume. It offers easy-to-use APIs for managing agent state, memory, and user interactions— which makes building dynamic experiences more accessible.

‍

Once you're ready to ship to production, use LangGraph Platform to gracefully handle large workloads, with features like retries and cost-efficient execution for reliable performance. LangGraph Platform also includes  LangGraph Studio, which lets you gain visibility into how agents act, helping you prototype faster.

Which plan is right for me?

If you’re an individual that wants to deploy on your own infrastructure, the Developer plan is a great choice. For teams that want to self-serve LangGraph Platform and deploy to our managed Cloud service, check out the Plus plan. If you need more advanced administration, authentication and authorization, deployment options, support, or annual invoicing, the Enterprise plan is right for you.

I’ve hit my deployment limits. What can I do?

If you’ve reached the maximum number of deployments on your plan tier, please reach out to support@langchain.dev.

Can I pay by ACH?

Yes, we offer ACH payment on the Enterprise plan, and we’re happy to work with your procurement team to onboard as a new vendor.

How will billing work?

Enterprise plan customers are billed annually by invoice.

What can I expect from support?

On the Enterprise plan, you’ll get white-glove support with a Slack channel, a dedicated customer success engineer, and monthly check-ins to go over LangGraph questions. We can help with anything from debugging, agent and RAG techniques, evaluation approaches, and cognitive architecture reviews.

Where is my data stored?

On the Plus Plan, our Cloud SaaS deployments are hosted at smith.langchain.com, so data is stored in GCP us-central-1 or europe-west4. If you’re on the Enterprise plan, we can deliver LangSmith to run on your Kubernetes cluster in AWS, GCP, or Azure for self-hosted, or AWS only for BYOC - so that data never leaves your environment. For more information, check out our LangGraph Platform docs.

Will you train on the data that I send to LangGraph Platform?

We will not train on your data, and you own all rights to your data. See our Terms of Service for more information.

Ready to start shipping 
reliable GenAI apps faster?

Get started with LangChain, LangSmith, and LangGraph to enhance your LLM app development, from prototype to production.

Get a demoSign up for free