LangGraph Pricing: A Complete Breakdown for 2026

LangGraph has become one of the most popular frameworks for building long-running AI agents. Built by the creators of LangChain, it provides durable execution, checkpointing, human-in-the-loop workflows, and stateful orchestration.

LangGraph pricing confuses people for a simple reason: LangGraph the framework doesn't cost anything. It's open source, and you can build and run agents with it for free. What actually shows up on an invoice is everything around it, mainly LangGraph Platform for hosting and LangSmith for tracing and evaluation. If you're trying to budget for a production agent built on LangGraph, this is the guide that separates what's free from what isn't.

This is written for engineering teams evaluating LangGraph before committing real budget to it, whether that's a platform lead scoping a build-vs-buy decision or a developer trying to explain the eventual bill to a manager.

What's included vs what costs extra

The free tiers are genuinely usable for prototyping. Where teams get surprised is scale.

Trace overage is the big one. LangSmith Plus includes 10,000 traces, and a single agent run can generate dozens of traces once you count every LLM call, tool call, and subagent step. An agent handling a few thousand requests a day can burn through the included allotment inside a week, and the $2.50 per 1,000 overage adds up fast once you're running multiple agents in parallel.

Retention is priced separately from volume. The default 14-day window is fine for debugging last week's incident, but if you need traces for compliance or long-term evaluation, the 400-day tier costs twice as much per trace.

Seats are per person, not per team, so a five-person platform team on LangSmith Plus is $195/month before any usage at all.

And self-hosting LangGraph itself is free in the sense that there's no license fee, but you're still paying for the servers, the ops time, and whatever monitoring you bolt on yourself. Nobody hands you observability, credential management, or governance for free just because the framework is open source.

Does LangGraph Cost Money?

Yes, but the answer depends on which LangGraph product you're using. The core LangGraph framework is completely free and open source under the MIT license. You can download it, build AI agents, and deploy them on your own infrastructure without paying any licensing fees.

However, if you want managed hosting, enterprise support, or integrated deployment tooling, LangChain also offers LangGraph Platform, a commercial product that starts at $35/month. Teams that need observability, debugging, and evaluation capabilities often add LangSmith, which has its own pricing tiers.

In other words, while getting started with LangGraph costs nothing, running production AI agents can involve several paid services depending on your requirements.

LangGraph pricing plans

A typical small production setup, LangSmith Plus plus LangGraph Platform, lands around $75 to $100 a month before you even add LLM API costs. That's a reasonable starting number, but it's a floor, not a ceiling.

At a high level:

• LangGraph (Framework) is free and gives you the core orchestration library.
• LangGraph Platform provides managed infrastructure for deploying and operating LangGraph applications.
• LangSmith is an optional developer platform for tracing, debugging, evaluation, and monitoring AI applications, available in Free, Plus, and Enterprise plans.

The right choice depends on whether you're experimenting with AI agents, deploying them to production, or operating them at enterprise scale.

One thing to flag here- pricing pages for developer tools change often, and the numbers above come from third-party pricing trackers rather than LangChain's own pricing page directly. Worth a quick check against langchain.com before you finalize a budget.

LangGraph Open Source Pricing

The LangGraph framework is completely free to use and is released under the MIT License. There are no licensing fees, usage limits, or restrictions on commercial use.

With the open-source version, you can build sophisticated agentic applications using features such as:

• Stateful agent workflows
• Multi-agent orchestration
• Durable execution with checkpointing
• Human-in-the-loop approval flows
• Long-term memory
• Custom graph-based execution logic

This makes the framework an excellent choice for:

• Individual developers learning agent frameworks
• Startups building MVPs
• Research and experimentation
• Internal prototypes and proof-of-concepts

That said, the open-source framework only solves the orchestration layer. You'll still need to provision and manage your own infrastructure, deploy applications, monitor performance, secure APIs, and scale workloads as usage grows. For many organizations, these operational requirements become the primary cost of running LangGraph in production.

LangSmith Pricing

While LangGraph handles agent orchestration, LangSmith is LangChain's platform for debugging, tracing, evaluating, and monitoring LLM applications. Although it's an optional product, many teams use it alongside LangGraph to gain visibility into how their agents behave in production. LangSmith is available in three pricing tiers:

Free (Developer)

The Developer plan is designed for individual developers and small projects. It includes:

• 5,000 traces per month
• 14-day trace retention
• One user seat

This plan is sufficient for experimentation and early-stage development.

Plus

The Plus plan costs $39 per seat per month and is intended for growing teams that require more observability.

It includes:

• 10,000 traces per month
• Additional traces billed at $2.50 per 1,000 traces
• Optional extended retention (up to 400 days) at $5.00 per 1,000 traces

Enterprise

The Enterprise plan offers custom pricing and includes features such as:

• Single Sign-On (SSO)
• Custom data retention policies
• Higher trace limits
• Dedicated support
• Enterprise-grade security and administration

LangChain doesn't publicly disclose Enterprise pricing, so organizations need to contact the sales team for a customized quote. Although LangSmith isn't required to use LangGraph, it's often a valuable addition for teams that need comprehensive debugging, evaluation, and monitoring capabilities for production AI applications.

Total cost of ownership considerations

The sticker price is one thing. What it takes to run this in production is another.

Most teams end up managing two separate vendor relationships: LangChain for LangGraph Platform and hosting, LangSmith for tracing, plus their own LLM provider bills on top of both. None of it is unified into a single invoice or a single place to set budgets.

Neither LangGraph Platform nor LangSmith manages credentials for the tools your agents call. If your agents use MCP servers or hit internal APIs, you're building your own layer for auth, rate limiting, and per-agent cost tracking, or buying one separately. That's a real cost that doesn't show up in the pricing table above.

This is the gap platforms like TrueFoundry's Agent Harness are built to close: model access, MCP tool governance, and observability live in one control plane instead of three separate systems you have to wire together yourself. Worth a look if the multi-vendor math above is starting to feel heavier than the framework itself.

Conclusion

LangGraph has established itself as one of the leading frameworks for building stateful AI agents, offering a powerful open-source foundation for everything from simple workflows to complex multi-agent systems. The framework itself is free to use, making it an attractive choice for developers and startups getting started with agentic AI.

However, the cost of running LangGraph in production extends beyond the framework. Infrastructure, LLM inference, observability, security, and ongoing engineering effort all contribute to the total cost of ownership. Teams should evaluate these operational expenses alongside LangGraph Platform and LangSmith pricing when planning production deployments.

For organizations building enterprise AI applications, the right choice depends on how much operational responsibility they want to manage themselves. While some teams prefer to self-host and customize every component, others may benefit from managed platforms that provide deployment, scaling, governance, and observability out of the box.

By understanding both the published pricing plans and the hidden costs involved, you can make a more informed decision about whether LangGraph fits your technical requirements, budget, and long-term AI strategy.

If you're building on LangGraph and starting to think about model governance, MCP access control, or VPC deployment, see how Agent Harness handles that layer.

FAQ

Is LangGraph pricing free?

‍LangGraph the framework is free and open source. You only pay if you use LangGraph Platform for hosted deployment (from $35/month) or LangSmith for tracing and evaluation (free tier available, $39/seat/month for Plus).

What does LangGraph cost for production use?

‍For a small team, LangSmith Plus plus LangGraph Platform runs somewhere between $75 and $150 a month, before LLM API costs and before trace overage. Larger teams with more seats or higher trace volume should expect that number to climb well past it.

Is LangSmith required to use LangGraph?

‍No. LangGraph runs fine without LangSmith. You lose the built-in tracing and evaluation dashboard, so most teams running anything beyond a prototype end up adopting some observability layer, whether that's LangSmith or something else.

Does TrueFoundry support MCP and AI agents?

‍Yes. TrueFoundry includes an MCP Gateway, an Agent Gateway, and an MCP and Agents Registry with tool-level access control. Agents built on LangGraph, CrewAI, AutoGen, or custom frameworks can be deployed and governed through the same control plane.

Does TrueFoundry integrate with my existing observability stack?

‍Yes. The platform is OpenTelemetry-compliant and plugs into Grafana, Datadog, Prometheus, or whatever you're already running, tracing each request from prompt through tool and model execution.