Sold by: LangChain
Deployed on AWS
LangSmith provides tools for developing, debugging, and deploying LLM applications. It helps you trace requests, evaluate outputs, test prompts, and manage deployments in one place.
LangSmith is framework agnostic, so you can use it with or without LangChain open-source libraries langchain and langgraph.
Prototype locally, then move to production with integrated monitoring and evaluation to build more reliable AI systems.
LangSmith provides:
- Observability to see exactly how your agent thinks and acts with detailed tracing and aggregate trend metrics.
- Evaluation to test and score agent behavior on production data and offline datasets for continuous improvement.
- Deployment to ship your agent in one click, using scalable infrastructure built for long-running tasks.
4.5
Overview
LangSmith Observability and Evals is a unified observability & evals platform where teams can debug, test, and monitor AI app performance - whether building with LangChain or not.
Find failures fast with agent observability. Quickly debug and understand non-deterministic LLM app behavior with tracing. See what your agent is doing step by step, then fix issues to improve latency and response quality.
Evaluate your agent's performance. Evaluate your app by saving production traces to datasets, then score performance with LLM-as-Judge evaluators. Gather human feedback from subject-matter experts to assess response relevance, correctness, harmfulness, and other criteria.
Experiment with models and prompts in the Playground, and compare outputs across different prompt versions. Any teammate can use the Prompt Canvas UI to directly recommend and improve prompts.
Track business-critical metrics like costs, latency, and response quality with live dashboards, then get alerted when problems arise and drill into root cause.
LangSmith Deployments is a purpose-built infrastructure and management layer for deploying and scaling long-running, stateful agents -- offering:
- 1-click deployment to go live in minutes,
- 30 API endpoints for designing custom user experiences that fit any interaction pattern
- Horizontal scaling to handle bursty, long-running traffic
- A persistence layer to support memory, conversational history, and async collaboration with human-in-the-loop or multi-agent workflows
- Native LangSmith Studio, the agent IDE, for easy debugging, visibility, and iteration
LangSmith Agent Builder: Give every team the ability to build, use, and improve AI agents with the security your org requires.
Highlights
- LangSmith Observability and Evals is a unified observability & evals platform where teams can debug, test, and monitor AI app performance - whether building with LangChain or not. Quickly debug and understand non-deterministic LLM app behavior with tracing. See what your agent is doing step by step, then fix issues to improve latency and response quality.
- LangSmith Deployments is a purpose-built infrastructure and management layer for deploying and scaling long-running, stateful agents offering 1/1-click deployment to go live in minutes, 2/Horizontal scaling to handle bursty, long-running traffic 3/A persistence layer to support memory, conversational history, and async collaboration with human-in-the-loop or multi-agent workflows.
- Please note: there is a $150k annual Platform License plus a minimum $150k annual usage commitment to access this package. To discuss enterprise pricing or to activate your commitment and obtain your license key after signup, please contact us at https://www.langchain.com/contact-sales - alternatively, our self-serve cloud-based products are available at https://www.langchain.com
Details
Sold by
Categories
Delivery method
Supported services
Delivery option
LangSmith Helm Chart
Latest version
Operating system
Linux
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Trust Center
Access real-time vendor security and compliance information through their Trust Center powered by Drata or Vanta. Review certifications and security standards before purchase.
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Cost/unit |
|---|---|
Per Trace | $0.01 |
Per Agent Run | $0.01 |
Metered Usage Amount | $0.01 |
Minimum annual usage commitment, billed in advance | $150,000.00 |
Per Agent Builder Run | $0.10 |
Dimensions summary
You pay based on what you use across five independent metrics. Per Trace bills you for each application execution you record and store. Per Agent Run and Per Agent Builder Run charge for agent executions and agent-building activity. Metered Usage Amount captures compute and storage consumed by platform services. These usage metrics accumulate as your work grows, so costs scale with activity rather than fixed seats. The Minimum annual usage commitment is billed in advance, setting a prepaid baseline of usage for the year. Actual charges depend on the work your agents perform.
Top-of-mind questions for buyers
A trace records a single execution of your application, such as an agent, evaluator, or playground session. One trace can hold many steps, including model calls and other tracked events. Base traces keep data for 14 days. You can upgrade base traces to extended traces with 400-day retention for an added fee.
Metered Usage Amount captures compute and storage used by platform services. Compute is measured in LangChain Compute Units and storage in LangChain Storage Units. Different services meter at different rates. Deployments and sandboxes bill per second while running, so idle serverless deployments that scale to zero stop accruing compute charges.
Per Trace, Per Agent Run, Per Agent Builder Run, and Metered Usage Amount all bill independently and add together on one invoice. Your prepaid annual commitment sets a baseline of usage bought in advance. As your work grows, charges accumulate against that baseline, then continue as pay-as-you-go once it is consumed.
www.langchain.com
Helpful?
Vendor refund policy
https://www.langchain.com/terms-of-service#:~:text=Customer%20will%20pay%20LangChain%20all ,Fees%20paid%20are%20non%2Drefundable.
Custom pricing options
Request a private offer to receive a custom quote.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
LangSmith Helm Chart
Supported services: Learn more
- Amazon EKS
Helm chart
Helm charts are Kubernetes YAML manifests combined into a single package that can be installed on Kubernetes clusters. The containerized application is deployed on a cluster by running a single Helm install command to install the seller-provided Helm chart.
Version release notes
LangSmith 0.13.14 release
Additional details
Usage instructions
See https://docs.smith.langchain.com/self_hosting for full installation and configuration instructions.
Resources
Vendor resources
Support
Vendor support
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
LangSmith is an agent engineering platform to build, test, deploy and observe your agents. It helps you trace requests, evaluate outputs, test prompts, and manage deployments in one place. LangSmith is framework agnostic, so you can use it with or without LangChain open-source libraries langchain and langgraph. Prototype locally, then move to production with integrated monitoring and evaluation to build more reliable AI systems. LangSmith provides: - Observability to see exactly how your agent thinks and acts with detailed tracing and aggregate trend metrics. - Evaluation to test and score agent behavior on production data and offline datasets for continuous improvement. - Deployment to ship your agent in one click, using scalable infrastructure built for long-running tasks.
Kriv AI instruments your Claude-on-Bedrock agents with OpenTelemetry + AWS X-Ray + Amazon CloudWatch GenAI Observability. Defines SRE-grade Service Level Objectives (latency p95 / p99, success rate, tool-use correctness, grounding score, cost-per-successful-invocation) with error budgets. Alerts to PagerDuty / Opsgenie / Jira / ServiceNow / Slack / Microsoft Teams. Runbook library + blameless post-mortem templates (Google SRE format). Hybrid engagement: $40K 3-week Implementation + optional $8K / $14K / $20K monthly Managed-Service retainer (up to 3 / 10 / unlimited agents). 12-month minimum term on retainer. Enterprise tier adds 0.25 FTE dedicated Kriv SRE engineer embedded with Customer SRE team + regulated-industry evidence (SOC 2 CC7 + SR 11-7 + EU AI Act Article 72 + HIPAA §164.308(a)(1)(ii)(D)). AWS Select + Databricks + Anthropic CPN.
Observability, prompt management and evaluation for LLM applications.
We help customers design and implement Agentic applications on AWS using our modular GenAI Building Block approach. Our experts support rapid PoCs and production deployments, guiding you in selecting and integrating the right LLM for your use case. This ensures flexibility, scalability, and cost-efficiency in your AWS environment.
This product has charges associated with it for hardening, security configuration, and support.
Langflow is an open-source visual framework for building multi-agent and RAG AI applications. This Lynxroute build is security baked in: authentication enabled, Nginx TLS reverse proxy, unique admin credentials at first boot, and CIS Level 1 hardened Ubuntu 24.04 LTS base.
Note: Langflow initialises in ~60 seconds after instance start. Wait 1-2 minutes before opening the Web UI.
MIT license - fully auditable, no vendor lock-in.
Customer reviews
Information Technology and Services
How langchain help us to create rags an solve production problem
Reviewed on Jul 30, 2026
Review provided by G2
What do you like best about the product?
To create rags
It helps to use multiple model with easy setup
It helps to use multiple model with easy setup
What do you dislike about the product?
Need to add multiple package like if I want to add multiple model
Like cheatopenai
Also documents needed to bit clear it's hard to find something
Like cheatopenai
Also documents needed to bit clear it's hard to find something
What problems is the product solving and how is that benefiting you?
We have created one rag for our AI service
Which solve our one complex problem
Which solve our one complex problem
Architecture & Planning
Easy No-Code AI Bot Building for Non-Coders
Reviewed on Jul 30, 2026
Review provided by G2
What do you like best about the product?
From someone who doesnt know any code and doesnt understand it, the option to build my own ai bot without code is great. It makes it quite easy to build a bot agent, but it can be quite tricky with all the user interface, but it is very possible for someone who doesnt understand code
What do you dislike about the product?
if you build a ai bot agent with the "build without code" option you can be limited as to what it can do. if you want something more intense for your operations or projects so to speak then you will need to understand some code. The User interface took me a long while to understand and I was confused at the starting process.
What problems is the product solving and how is that benefiting you?
I was able to set it so that it can read some documents and help me understand what it is being said in them. I could also send it the documents and if I wanted to search for something within these documents it could read it and send it to me very quickly, saving me a lot of time
Information Services
Flexible Framework for Rapid LLM Prototyping
Reviewed on Jul 30, 2026
Review provided by G2
What do you like best about the product?
What I like best about LangChain is its flexibility and extensive ecosystem for building LLM-powered applications. It provides a structured way to create RAG workflows, AI agents, prompt pipelines, and tool integrations without having to build every component from scratch. The wide range of integrations with LLMs, vector databases, APIs, and data sources makes it easy to experiment with different architectures and technologies.
It has significantly improved my workflow by reducing development effort during prototyping and allowing me to focus on application logic rather than boilerplate integration code. The framework is powerful enough for complex AI use cases while still supporting rapid proof-of-concept development. I also appreciate the active community, extensive documentation, and the ability to combine retrieval, memory, tools, and agent capabilities into a single workflow. From an ROI perspective, it helps accelerate AI development and reduces the time required to validate new ideas.
It has significantly improved my workflow by reducing development effort during prototyping and allowing me to focus on application logic rather than boilerplate integration code. The framework is powerful enough for complex AI use cases while still supporting rapid proof-of-concept development. I also appreciate the active community, extensive documentation, and the ability to combine retrieval, memory, tools, and agent capabilities into a single workflow. From an ROI perspective, it helps accelerate AI development and reduces the time required to validate new ideas.
What do you dislike about the product?
One challenge with LangChain is that the framework has a fairly steep learning curve when moving beyond basic examples. Because it offers many abstractions, integrations, and components, it can take time to understand the best patterns for a specific use case. Frequent updates and changes in APIs can also require developers to revisit existing code and documentation.
For complex workflows, debugging and observability can sometimes be challenging because multiple layers of chains, agents, tools, and retrieval components are involved. While the ecosystem is powerful, new users may benefit from more end-to-end examples, migration guides, and production-focused best practices. Overall, the flexibility is a major strength, but it can also introduce additional complexity for onboarding and maintenance.
For complex workflows, debugging and observability can sometimes be challenging because multiple layers of chains, agents, tools, and retrieval components are involved. While the ecosystem is powerful, new users may benefit from more end-to-end examples, migration guides, and production-focused best practices. Overall, the flexibility is a major strength, but it can also introduce additional complexity for onboarding and maintenance.
What problems is the product solving and how is that benefiting you?
Before using LangChain, building LLM-powered applications required significant custom code to handle prompt orchestration, model interactions, retrieval pipelines, memory, and tool integrations. LangChain helps solve this by providing a structured framework that brings these components together in a reusable and modular way.
The biggest benefit for me is faster development and experimentation. Instead of creating every integration and workflow from scratch, I can focus on the business logic while using LangChain for orchestration, retrieval, agent workflows, and tool calling. This significantly reduces boilerplate code and accelerates proof-of-concept development.
From a business perspective, LangChain helps validate AI use cases more efficiently, including RAG applications, document Q&A, knowledge search, and AI assistants. Its broad ecosystem of integrations makes it easier to connect models, vector databases, APIs, and enterprise data sources, which shortens development cycles and improves productivity. The framework enables rapid prototyping while still providing the flexibility needed to scale more advanced AI workflows.
The biggest benefit for me is faster development and experimentation. Instead of creating every integration and workflow from scratch, I can focus on the business logic while using LangChain for orchestration, retrieval, agent workflows, and tool calling. This significantly reduces boilerplate code and accelerates proof-of-concept development.
From a business perspective, LangChain helps validate AI use cases more efficiently, including RAG applications, document Q&A, knowledge search, and AI assistants. Its broad ecosystem of integrations makes it easier to connect models, vector databases, APIs, and enterprise data sources, which shortens development cycles and improves productivity. The framework enables rapid prototyping while still providing the flexibility needed to scale more advanced AI workflows.
Elmarie D.
Turns Compliance Knowledge Into a Flexible, Powerful AI Assistant
Reviewed on Jul 30, 2026
Review provided by G2
What do you like best about the product?
We love the ability to turn our existing compliance knowledge into an amazingly useful AI assistant without locking the business into one AI provider.
What do you dislike about the product?
The ongoing maintenance requirements and technical complexity are a drawback.
What problems is the product solving and how is that benefiting you?
Langchain is solving the problem of answering repetitive service desk queries by doing the answering for us. It also allows us to have an assistant that searches our policies, legislation, training material, FAQs and internal guidance documents.
Program Development
AI applications in natural language – with practical memory modules
Reviewed on Jul 29, 2026
Review provided by G2
What do you like best about the product?
This enables the development of AI applications that can interact with data, tools, and even users in natural language. Built-in memory modules significantly simplify the management of conversation histories.
What do you dislike about the product?
Developers often have to read a lot of code to understand even trivial functions. Additionally, programming skills are required, which can be a real challenge for beginners.
What problems is the product solving and how is that benefiting you?
LangChain primarily solves the major practical hurdles for us that arise when trying to build real, production-ready applications from pure Large Language Models (LLMs). It addresses the typical problems that occur during the development of such applications.