--- title: Langfuse for Enterprise description: FAQ and deployment options for Langfuse in an enterprise environment. --- # Langfuse for Enterprise Langfuse is the leading AI Engineering platform built for enterprise-grade security, scalability, and compliance. Trusted by **21 of the Fortune 50** and **129 of the Fortune 500**, Langfuse addresses key challenges when deploying LLM-based applications within an enterprise environment. Langfuse is the most widely adopted LLM Engineering platform: - Used by **50,000+** companies - **34,321** GitHub stars - **65M+** SDK installs per month - **38M+** Docker pulls - Trusted by **21 of the Fortune 50** and **129 of the Fortune 500** ## A complete toolbox to build enterprise LLM applications Langfuse is a complete platform combining [[1] observability](/docs/observability/overview), [[2] prompt management](/docs/prompt-management/overview), [[3] evaluation](/docs/evaluation/overview), and much more to help teams collaboratively debug, analyze, and iterate on their LLM applications. All platform features are natively integrated to accelerate the development workflow. **Langfuse is open, self-hostable, and extensible.** Please refer to our [feature overview](/docs) to learn about all the features and how to get started. ## Enterprise grade scalability and security **Langfuse Cloud** is enterprise-ready with SOC 2 Type II and ISO 27001 certifications, GDPR compliance, and HIPAA alignment. For organizations with specific data residency requirements, Langfuse can also be [self-hosted](/self-hosting) as an [open source](/open-source) MIT-licensed project. For government and other highly regulated environments, we are extending Langfuse Self-Hosted Enterprise with FIPS-compatible deployment support, hardened deployment images, air-gapped operation, and end-to-end deployment documentation for Langfuse and its required subcomponents. See [Hardening for Government](/self-hosting/configuration/hardening#hardening-for-government) for details and current availability. Langfuse **scales to the largest enterprise use cases** and platform deployment scenarios. Langfuse OSS and Langfuse Enterprise use the same codebase as Langfuse Cloud. Langfuse Cloud currently operates at: - **\>80M** traces per day - **\>5B** tracing events per month - **Thousands of customers** on the same multi-tenant deployment ## Packages & Services We offer a range of packages and services to help you get started with Langfuse. - **Langfuse Cloud** [(see plans and what's included)](/pricing) - **Self-host Langfuse** for free or with an Enterprise Agreement [(see self-host licensing)](/pricing-self-host) More details: - Langfuse can be procured through AWS Marketplace or per invoice. [Talk to us](/talk-to-us) to request a private Marketplace offer. - With an Enterprise Agreement, you get access to additional support, features to address your specific needs and compliance requirements. ## Don't take our word for it ## Let's Talk! Ready to get started with Langfuse Enterprise? We're here to help you find the right solution for your team. export function TalkToUsButton() { return ( ); } ## Additional Resources ### Ways to experience the Product - [Test it yourself with our demo-application](/docs/demo) of the Langfuse platform - [Create an account on Langfuse Cloud](https://langfuse.com/cloud) for free (no credit card required) - [Talk to Sales](/talk-to-us) to get a personalized demo ### Product - [Why customers choose Langfuse](/why) - [Security and Compliance](/security) - about GDPR, HIPAA, SOC2 and ISO27001 compliance and [related FAQs](/security/security-faq) - [Technical documentation](/docs) - [Changelog](/changelog) - [Roadmap](/docs/roadmap) ### Langfuse Cloud - [Cloud Pricing](/pricing) - [Security and Compliance](/security) - includes information on GDPR, HIPAA, SOC2 and ISO27001 compliance ### Self-hosting - [Deployment Guide](/self-hosting) - [Open Source Licensing](/open-source) - [Comparison](/pricing-self-host) of Open Source and Enterprise version - [Langfuse Self-Hosting: EE](/self-hosting) [Terms and Conditions](/terms) ### Webinars - [Traces as the core of the LLMOps workflow (webinar + slides)](/resources/engineering/webinar-observability-llm-systems) - [Continuous Agent Evals with Langfuse and AWS Bedrock AgentCore](https://www.youtube.com/watch?v=api-Z4TfDvM) ### Langfuse implementation partners Need help implementing agents, instrumenting Langfuse, or supporting a deployment? [Explore Langfuse partners](/partners). ## Any questions? We're here to help you find the right solution for your use case. ## FAQ We collect the most common questions and answers here. If you have questions that are not answered, please [contact sales](/talk-to-us).
What deployment options are available for Langfuse? 1. Managed Cloud (cloud.langfuse.com), see [Pricing](/pricing) and [Security](/security) page for details. 2. [Self-hosted](/self-hosting) on your own infrastructure. Contact us if you are interested in additional support.
Can I purchase Langfuse through AWS Marketplace? Yes. Langfuse is available via AWS Marketplace as a private offer. [Talk to us](/talk-to-us) and we will share an offer you can accept in your AWS account. Invoice billing is also available.
Does Langfuse support government and air-gapped deployments? We are actively developing additional hardening capabilities for Langfuse Self-Hosted Enterprise, including FIPS-compatible deployment support, hardened deployment images, air-gapped operation, and documentation for running the complete deployment stack and its required subcomponents. See [Hardening for Government](/self-hosting/configuration/hardening#hardening-for-government) for details, or [contact sales](/talk-to-us?deployment=self-hosted) to discuss your requirements and early access.
Support SLO for our enterprise customers For current support availability, response targets, and severity definitions, see the [ClickHouse Support Services Policy](https://clickhouse.com/legal/support-services-policy). Your applicable support terms are defined in your agreement and may be customized upon request.
Uptime SLA for our enterprise customers Our Enterprise Cloud customers get an uptime SLA on Langfuse Cloud: **Target:** 99.9% Monthly Uptime Percentage. **Service credits** apply when monthly uptime falls below target: - Below 99.9% but at or above 99.0% — 5% credit - Below 99.0% but at or above 95.0% — 10% credit - Below 95.0% — 25% credit Langfuse Cloud is considered "Unavailable" for a one-minute interval when at least three authenticated trace-ingestion API requests were made during that interval and none were accepted. Uptime calculations exclude downtime caused by force majeure events, third-party services outside our control, customer misconfiguration or improper use, planned maintenance announced at least 72 hours in advance, and beta or experimental features. To claim a credit, open a support case within 24 hours of discovering the unavailability and submit the claim by the end of the month following the affected month, including the incident dates, times, and supporting evidence. See the full [Langfuse Cloud Service Level Agreement](https://clickhouse.com/legal/agreements/langfuse-service-level-agreement) for the authoritative terms.
What is the difference between Langfuse Cloud and the open-source version? The Langfuse team provides Langfuse Cloud as a managed solution to simplify the initial setup of Langfuse and to minimize the operational overhead of maintaining high availability in production. You can choose to self-host Langfuse on your own infrastructure. Some features are not available in the open-source version. Please refer to the overview [here](/pricing-self-host).
How does Authentication and RBAC work in Langfuse? Langfuse offers a list of prebuilt roles which apply on an organizational and project level to restrict access ([RBAC documentation](/docs/rbac)). If needed, environments (production, staging, development) can be separated into different projects in Langfuse to restrict access to production/sensitive data while making it easier to share development environments with the team and other stakeholders. SSO with Langfuse is simple. Currently Google, GitHub, Azure AD, Okta, Auth0, AWS Cognito, Keycloak, and JumpCloud are supported. We can easily add additional providers based on your requirements. As an enterprise customer, you can also enforce SSO for your organization.
What is the easiest way to try Langfuse? The Hobby Plan on [Langfuse Cloud](/cloud) includes enough resources to try Langfuse for free while in a non-production environment, no credit card required. Alternatively, you can quickly spin up Langfuse on your own machine using `docker compose up` ([docs](/self-hosting/deployment/docker-compose)). If you require security and compliance features to run a POC, please [contact sales](/talk-to-us).
Common Enterprise LLM Platform Architecture Langfuse aims to address the challenges of debugging, monitoring, and continuously improving LLM-based applications. It focuses on observability, evaluation, and prompt management. Langfuse is often deployed alongside a central LLM Gateway that provides schema translation, rate limiting, and PII redaction. The LLM Gateway can be an internal service or an open-source project like LiteLLM. If you use LiteLLM, you can leverage the native integration ([docs](/integrations/gateways/litellm)). ```mermaid graph LR LLM["LLM
API or service"] App["Application"] LF["Langfuse
Tracing/Observability
Evaluation
Prompt Management
Cost Tracking
Security Monitoring
Experiments
... (see docs)"] Gateway["LLM Gateway (optional)
Internal or Open-source (e.g. LiteLLM)
Schema translation
Rate limiting
PII redaction"] App -->|async tracing|LF LF -->|prompt management| App LLM --- App LLM --- Gateway --- App Gateway -->|"optional: forward llm calls"| LF ```
--- ## Agent Instructions This page is part of the [Langfuse](https://langfuse.com) documentation, published as plain Markdown for AI agents. Every page is available as Markdown by appending `.md` to its URL, or by sending an `Accept: text/markdown` header. This page: `https://langfuse.com/enterprise.md`. ### Querying these docs If the answer is not on this page, query the documentation instead of guessing: - **Semantic search** across all Langfuse docs, returning an answer with the relevant pages and excerpts. Ask a specific, self-contained question: ```bash curl -sG "https://langfuse.com/api/search-docs" --data-urlencode "query=How do I trace a LangGraph agent?" ``` - **Index of every page**: , with per-section indexes [llms-docs.txt](https://langfuse.com/llms-docs.txt), [llms-integrations.txt](https://langfuse.com/llms-integrations.txt), and [llms-self-hosting.txt](https://langfuse.com/llms-self-hosting.txt). ### Before writing Langfuse code - **Install the [Langfuse Agent Skill](https://langfuse.com/docs/api-and-data-platform/features/agent-skill).** It encodes Langfuse's own best practices for instrumentation, prompt management, and evaluation, and materially improves results. - **Read [What does a good trace look like?](https://langfuse.com/docs/observability/best-practices.md)** before instrumenting an application. - **Verify endpoints, parameters, and response fields** against the [API reference](https://api.reference.langfuse.com) instead of inferring them from code examples. - **Use the [Langfuse CLI](https://langfuse.com/docs/api-and-data-platform/features/cli)** (`npx langfuse-cli api `) to read or write traces, prompts, datasets, and scores from the terminal. Found an error in these docs? Please open an issue at .