Sold by: LangWatch
LangWatch helps AI platform teams test, evaluate, observe and govern every AI agent and LLM call in their company. You can simulate agents before release, run evals on live production traffic, and trace every step with OpenTelemetry. One AI gateway controls cost and access across providers, including Amazon Bedrock. It is open source under Apache 2.0, ISO 27001 certified and GDPR compliant.
Overview
LangWatch gives AI platform teams one place to test, observe, route and govern all the AI their company builds and uses, from custom agents in production to the coding assistants engineers use every day.
Agent testing and simulation Simulated users push your agents through realistic text and voice conversations over many turns. You can write scenarios in plain language and run the same ones locally and in CI on every pull request. Red-team simulations look for jailbreaks, policy breaks and unsafe tool calls. A trace-reading judge explains every verdict.
Evaluations Use LLM-as-a-judge, custom code or workflow evaluators on single outputs or full conversations. Online evaluations score production traffic in real time. Instant Evals answer quality questions across your production history on demand. Pairwise comparison and multimodal evaluation are included.
Observability LangWatch is OpenTelemetry-native, with full GenAI spec support. It traces every agent step, tool call and MCP server, with token, cost and cache accounting per span. You get waterfall, flame graph and topology views, natural-language search, conversation clustering and custom dashboards for cost, latency and quality.
AI Gateway One endpoint for every AI call, using your own keys for Amazon Bedrock, OpenAI, Anthropic, Azure OpenAI, Google Gemini, Mistral and more. You can set budgets per person, team and customer, and attribute cost to cost centers.
Langy, the automated AI engineer Langy reads traces, writes tests and opens pull requests. Product managers and domain experts can then improve agents directly, while engineers approve every change.
Coding agent usage tracking See token spend, real cost per person and team, and full session history for Claude Code, Codex, GitHub Copilot, Cursor and other coding agents.
Prompt management Version, deploy and A/B test prompts, with GitHub sync.
Enterprise ready SSO, SCIM, RBAC, audit log export to your SIEM, custom retention policies and REST APIs. LangWatch is ISO 27001 certified and GDPR compliant, with EU data residency. Run it as managed cloud, as a hybrid with the data plane in your own infrastructure, or self-hosted in your VPC on Docker or Kubernetes.
Works with LangChain, LangGraph, CrewAI, OpenAI Agents, Pydantic AI, Mastra, Vercel AI SDK, DSPy, n8n and any framework through OpenTelemetry, with SDKs for Python, TypeScript and Go.
Trusted by teams at Deloitte, Backbase, PagBank and Visma.
For enterprise plans, self-hosted or hybrid deployment, contact sales@langwatch.ai .
Highlights
- Agent testing and simulation: realistic text and voice scenarios, red-teaming and CI checks on every pull request, so issues surface before your users find them.
- Evaluations and OpenTelemetry-native observability: online evals on production traffic, per-span cost and token tracking, and dashboards for quality, latency and spend.
- AI Gateway and governance: one endpoint across Amazon Bedrock and other providers, budgets per team, SSO, RBAC and audit logs. ISO 27001 certified and GDPR compliant.
Details
Sold by
Categories
Delivery method
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
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 the duration and terms of your contract with the vendor. This entitles you to a specified quantity of use for the contract duration. If you choose not to renew or replace your contract before it ends, access to these entitlements will expire.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/month |
|---|---|---|
traces | Traces running through the platform | $3,490.00 |
Dimensions summary
This contract charges by traces, the units of work your AI applications send through the platform. A trace captures each LLM call, tool call, retrieval, evaluation, or simulation step. Because most AI interactions generate several of these events, your cost scales with how much activity you process. You commit to a quantity of traces under the contract, and billing follows that usage-based measure. There is one pricing dimension here, so cost rises or falls with the volume of traces your workloads produce rather than with seats or fixed feature tiers.
Top-of-mind questions for buyers
A trace captures the work your AI application performs on the platform. Each LLM call, tool call, retrieval, evaluation, or simulation step counts. One user interaction often generates several of these events, since an agent may retrieve information, call a model, use tools, then run quality checks.
Cost follows the volume of traces your applications send. Busier agents that make more model calls, tool calls, retrievals, and evaluations produce more traces, so your charges rise with that activity. Quieter periods produce fewer traces and lower usage. The single trace metric drives the bill.
Yes. The platform runs fully self-hosted on your own servers and database, so data stays in your environment. You can start managed and move to hybrid or self-hosted later. Deployment choice does not change that billing here is measured by traces.
langwatch.ai+1
Helpful?
Vendor refund policy
- The Client shall notify LangWatch in writing of any complaints within 14 days after it discovers a possible shortcoming or fault or should reasonably have discovered the shortcoming or fault of any aspect of the (services related to) the Platform. 2. A timely notified complaint does not suspend or cancel any (payment) obligation of the Client. 3. If the Client does not notify LangWatch on time, the Client is not entitled to any recovery performance or compensation.
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
Software as a Service (SaaS)
SaaS delivers cloud-based software applications directly to customers over the internet. You can access these applications through a subscription model. You will pay recurring monthly usage fees through your AWS bill, while AWS handles deployment and infrastructure management, ensuring scalability, reliability, and seamless integration with other AWS services.
Resources
Vendor resources
Support
Vendor support
How to reach us
- Email: support@langwatch.ai
- Documentation: https://langwatch.ai/docs
- Open source and issues: https://github.com/langwatch/langwatch
All plans
- Email support from our engineering team
- Full documentation, integration guides and SDK references for Python, TypeScript and Go
- Help getting your first traces, evaluations and agent simulations running
Enterprise plans
- Dedicated shared Slack or Microsoft Teams channel with our team
- Response times guaranteed in your contract SLA
- Hands-on onboarding: integration with your agent framework, OpenTelemetry setup, and writing your first scenarios and evaluators
- Deployment support for hybrid and self-hosted setups in your own AWS account or VPC (Docker, Kubernetes/Helm)
- Regular check-ins with a named contact to review usage, evaluation coverage and roadmap
- Security and compliance support for your reviews (ISO 27001, GDPR, DPA, EU data residency)
For enterprise support packages and SLAs, contact sales@langwatch.ai .
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 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.
LangSmith is a framework-agnostic platform for building production AI agents. Trace, evaluate, and deploy agents with integrated observability and one-click deployment.
LangSmith BYOC deploys a fully managed agent observability, evaluation, and deployment platform inside your own AWS account and VPC, keeping sensitive data in your cloud boundary.
Geordie discovers, monitors, and secures AI agents across your enterprise. Go from connection to initial agent visibility in 10 minutes. RSAC 2026 Innovation Sandbox winner.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.