--- title: Pricing description: Simple pricing for projects of all sizes. Get started on our Hobby plan without a credit card. --- # Pricing Get started on the Hobby plan for free. No credit card required. See also: [Self-hosted pricing](/pricing-self-host). ## Cloud Plans ### Hobby (Free) Get started, no credit card required. Great for hobby projects and POCs. - All platform features (with limits) - 50k units / month included - 30 days data access - 2 users - Community support via GitHub Trusted by: [Hugging Face](/users/hugging-face) [Sign up](/cloud) ### Core ($29/month) For production projects. Longer data access and unlimited users. - Everything in Hobby - 100k units / month included, additional: $8/100k units (lower with volume) - 90 days data access - Unlimited users - In-app support Discounts available for [startups](/startups), [research/students](/research), and [open-source projects](/pricing#discounts). Trusted by: [Magic Patterns](/users/magic-patterns-ai-design-tools), Draftbit [Sign up](/cloud) ### Pro ($199/month) For scaling projects. Unlimited history, high rate limits, all features. - Everything in Core - 100k units / month included, additional: $8/100k units (lower with volume) - 3 years data access - Data retention management - Unlimited annotation queues - High rate limits - SOC2 & ISO27001 reports, BAA available (HIPAA) - Prioritized in-app support Optional **Teams Add-on** ($300/month): - Enterprise SSO (e.g. Okta) - SSO enforcement - Fine-grained RBAC - Support via dedicated Slack channel Trusted by: [Canva](/users/canva), Twilio, [SumUp](/users/sumup), Brevo [Sign up](/cloud) ### Enterprise ($2,499/month) For large-scale teams. Enterprise-grade support and security. - Everything in Pro + Teams - 100k units / month included, additional: $8/100k units (lower with volume) - Audit logs - SCIM API - Custom rate limits - Uptime SLA - Support SLA - Named lead support engineer Optional **Yearly Commitment**: - Custom volume pricing - Architecture reviews - Billing via AWS Marketplace - Billing via invoice - Vendor onboarding Trusted by: Ramp, GoDaddy, [Khan Academy](/users/khan-academy), [Merck Group](/users/merckgroup) [Contact sales](/talk-to-us?deployment=cloud) | [Enterprise FAQ](/enterprise) ## Feature Comparison (Cloud) | Feature | Hobby | Core | Pro | Enterprise | | ----------------------------------------------------------------------------------------------- | ------------------- | ------------------- | ------------------- | ---------------------------- | | **LLM Application & Agent Tracing** | | | | | | [Traces and graphs (agents)](/docs/observability/overview) | Yes | Yes | Yes | Yes | | [Session tracking (chats/threads)](/docs/observability/features/sessions) | Yes | Yes | Yes | Yes | | [User tracking](/docs/observability/features/users) | Yes | Yes | Yes | Yes | | [Token and cost tracking](/docs/observability/features/token-and-cost-tracking) | Yes | Yes | Yes | Yes | | [Native framework integrations](/integrations) | Yes | Yes | Yes | Yes | | [SDKs (Python, JavaScript)](/docs/observability/sdk/overview) | Yes | Yes | Yes | Yes | | [OpenTelemetry (Java, Go, custom)](/integrations/native/opentelemetry) | Yes | Yes | Yes | Yes | | [Proxy-based logging (via LiteLLM)](/integrations/gateways/litellm) | Yes | Yes | Yes | Yes | | [Custom via API](/docs/api-and-data-platform/features/public-api) | Yes | Yes | Yes | Yes | | [Included usage](/docs/administration/billable-units) | 50k units | 100k units | 100k units | 100k units | | [Additional usage](/docs/administration/billable-units) | -- | $8/100k units | $8/100k units | $8/100k units | | Custom usage pricing | -- | -- | -- | Yearly Commitment | | [Multi-modal](/docs/observability/features/multi-modality) | Free while in beta | Free while in beta | Free while in beta | Free while in beta | | Access to historical data | 30 days | 90 days | 3 years | 3 years | | [Ingestion throughput](/faq/all/api-limits) | 1,000 req/min | 4,000 req/min | 20,000 req/min | Custom | | **Langfuse AI** | | | | | | [Langfuse Assistant (in-app agent)](/docs/langfuse-assistant) | Yes | Yes | Yes | Yes | | Langfuse Assistant usage limits | Low | Medium | High | High | | **Prompt Management** | | | | | | [Prompt versioning](/docs/prompt-management/get-started) | Yes | Yes | Yes | Yes | | Prompt fetching | Unlimited | Unlimited | Unlimited | Unlimited | | [Prompt release management](/docs/prompt-management/features/prompt-version-control) | Yes | Yes | Yes | Yes | | [Prompt composability](/docs/prompt-management/features/composability) | Yes | Yes | Yes | Yes | | [Prompt caching (server and client)](/docs/prompt-management/features/caching) | Yes | Yes | Yes | Yes | | [Playground](/docs/prompt-management/features/playground) | Yes | Yes | Yes | Yes | | [Prompt experiments](/docs/evaluation/experiments/experiments-via-ui) | Yes | Yes | Yes | Yes | | [Webhooks & Slack](/docs/prompt-management/features/webhooks-slack-integrations) | Yes | Yes | Yes | Yes | | [Protected deployment labels](/docs/prompt-management/get-started#protected-prompt-labels) | -- | -- | Teams add-on | Yes | | **Evaluation (online and offline)** | | | | | | [Datasets](/docs/evaluation/experiments/datasets) | Yes | Yes | Yes | Yes | | [Experiments via SDK](/docs/evaluation/experiments/experiments-via-sdk) | Yes | Yes | Yes | Yes | | [Experiments via UI](/docs/evaluation/experiments/experiments-via-ui) | Yes | Yes | Yes | Yes | | [Evaluation scores (custom)](/docs/evaluation/evaluation-methods/scores-via-sdk) | Yes | Yes | Yes | Yes | | [User feedback tracking](/docs/observability/features/user-feedback) | Yes | Yes | Yes | Yes | | [External evaluation pipelines](/guides/cookbook/example_external_evaluation_pipelines) | Yes | Yes | Yes | Yes | | [LLM-as-judge evaluators](/docs/evaluation/evaluation-methods/llm-as-a-judge) | Yes | Yes | Yes | Yes | | [Human annotation](/docs/evaluation/evaluation-methods/scores-via-ui) | Yes | Yes | Yes | Yes | | [Human annotation queues](/docs/evaluation/evaluation-methods/annotation-queues) | 1 queue | 3 queues | Yes | Yes | | **Metrics** | | | | | | [Custom dashboards](/docs/metrics/features/custom-dashboards) | Yes | Yes | Yes | Yes | | [Alerts](/docs/observability/features/alerts) | 2 alerts | 20 alerts | 50 alerts | 100 alerts | | **Collaboration** | | | | | | Projects | Unlimited | Unlimited | Unlimited | Unlimited | | Users | 2 | Unlimited | Unlimited | Unlimited | | **API** | | | | | | [Extensive public API](/docs/api-and-data-platform/features/public-api) | Yes | Yes | Yes | Yes | | [Rate limit (General API)](/faq/all/api-limits) | 30 req/min | 100 req/min | 1,000 req/min | Custom | | [Rate limit (Datasets API)](/faq/all/api-limits) | 100 req/min | 200 req/min | 1,000 req/min | Custom | | [Rate limit (Metrics API v2)](/faq/all/api-limits) | 100 req/day | 100 req/hour | 500 req/hour | Custom | | [Rate limit (Observations API v2)](/faq/all/api-limits) | 30 req/min | 100 req/min | 1,000 req/min | Custom | | [Rate limit (Legacy Metrics API)](/faq/all/api-limits) | 100 req/day | 2,000 req/day | 2,000 req/day | Custom | | [SLA](/enterprise#faq) | -- | -- | -- | Yes | | **Exports** | | | | | | [Batch export via UI](/docs/api-and-data-platform/features/export-from-ui) | Yes | Yes | Yes | Yes | | [PostHog integration](/integrations/analytics/posthog) | Yes | Yes | Yes | Yes | | [Mixpanel integration](/integrations/analytics/mixpanel) | Yes | Yes | Yes | Yes | | [Scheduled export to blob storage](/docs/api-and-data-platform/features/export-to-blob-storage) | -- | -- | Teams add-on | Yes | | **Support** | | | | | | [Ask AI](/docs/ask-ai) | Yes | Yes | Yes | Yes | | [Community (GitHub)](/support#community) | Yes | Yes | Yes | Yes | | [In-app support](/support#in-app) | -- | Yes | Yes | Yes | | [Private Slack channel](/support#slack) | -- | -- | Teams add-on | Yes | | [Named lead support engineer](/support#onboarding) | -- | -- | -- | Yes | | [Onboarding & architectural guidance](/support#onboarding) | -- | -- | -- | Yes | | Response time SLO | n/a | 48h | 48h (Teams: 24h) | Custom | | [Support SLA](/enterprise#faq) | -- | -- | -- | Yes | | **Security** | | | | | | [Data region](/security/data-regions) | US, EU, or Japan | US, EU, or Japan | US, EU, or Japan | US, EU, Japan, or HIPAA | | [AWS PrivateLink](/security/networking) | -- | -- | -- | Yes\* | | Sign in with Google, AzureAD, GitHub | Yes | Yes | Yes | Yes | | [Organization-level RBAC](/docs/administration/rbac) | Yes | Yes | Yes | Yes | | Enterprise SSO (e.g. Okta, EntraID) | -- | -- | Teams add-on | Yes | | SSO enforcement | -- | -- | Teams add-on | Yes | | [Client-side data masking](/docs/observability/features/masking) | Yes | Yes | Yes | Yes | | [Project-level RBAC](/docs/administration/rbac#project-level-roles) | -- | -- | Teams add-on | Yes | | [Data retention management](/docs/administration/data-retention) | -- | -- | Yes | Yes | | [SCIM API (automated user provisioning)](/docs/administration/scim-and-org-api) | -- | -- | -- | Yes | | [Audit logs](/docs/administration/audit-logs) | -- | -- | -- | Yes | | **Billing** | | | | | | Subscription management | -- | Self-serve | Self-serve | Self-serve, or contact sales | | Payment methods | -- | Credit card | Credit card | Credit card, Invoice | | Contract duration | -- | Monthly | Monthly | Yearly Commitment | | Billing via AWS Marketplace | -- | -- | -- | Yearly Commitment | | **Compliance** | | | | | | Contracts | Standard T&Cs & DPA | Standard T&Cs & DPA | Standard T&Cs & DPA | Talk to sales | | [Data processing agreement (GDPR)](/security/dpa) | Yes | Yes | Yes | Yes | | [SOC2 Type II & ISO27001 reports](/security) | -- | -- | Yes | Yes | | [HIPAA compliance](/security/hipaa) | -- | -- | Yes | Yes | | InfoSec/legal reviews | -- | -- | -- | Yearly Commitment | \* Available for Enterprise customers with a committed contract and subject to regional availability. See [networking documentation](/security/networking) for details. ## Graduated Usage Pricing Additional usage beyond the included units is billed at graduated rates. Higher volumes automatically get lower rates: | Tier | Rate | | ---------------- | ------------------ | | 0 -- 100k units | Included in plan | | 100k -- 1M units | $8.00 / 100k units | | 1M -- 10M units | $7.00 / 100k units | | 10M -- 50M units | $6.50 / 100k units | | 50M+ units | $6.00 / 100k units | ### Pricing Examples **Example 1: Small project (200k units/month on Core)** - Core base fee: $29.00 - First 100k units: included - Next 100k units at $8.00/100k: $8.00 - **Total: $37.00/month** **Example 2: Growing project (1M units/month on Core)** - Core base fee: $29.00 - First 100k units: included - Next 900k units at $8.00/100k: $72.00 - **Total: $101.00/month** **Example 3: Scaling project (5M units/month on Pro)** - Pro base fee: $199.00 - First 100k units: included - Next 900k units at $8.00/100k: $72.00 - Next 4M units at $7.00/100k: $280.00 - **Total: $551.00/month** **Example 4: Large project (25M units/month on Pro + Teams)** - Pro + Teams base fee: $499.00 - First 100k units: included - Next 900k units at $8.00/100k: $72.00 - Next 9M units at $7.00/100k: $630.00 - Next 15M units at $6.50/100k: $975.00 - **Total: $2,176.00/month** **Example 5: Enterprise scale (100M units/month on Enterprise)** - Enterprise base fee: $2,499.00 - First 100k units: included - Next 900k units at $8.00/100k: $72.00 - Next 9M units at $7.00/100k: $630.00 - Next 40M units at $6.50/100k: $2,600.00 - Next 50M units at $6.00/100k: $3,000.00 - **Total: $8,801.00/month** (custom volume pricing available with yearly commitment) ### Billable Units A billable unit in Langfuse is any tracing data point sent to the platform -- including traces (complete application interactions), observations (individual steps: spans, events, and generations), and scores (evaluations). See [billable units documentation](/docs/administration/billable-units) for details. ## Discounts | Program | Discount | Details | | -------------------- | ----------------------------------- | ----------------------------------- | | Early-stage startups | 50% off, first year | [Learn more and apply](/startups) | | Research / Students | Up to 100% off (limits apply) | [Learn more and apply](/research) | | Non-profits | $199 in credits / month | [Learn more and apply](/non-profit) | | Open-source projects | $300 in credits / month, first year | Contact support@langfuse.com | ## Frequently Asked Questions **What is the easiest way to try Langfuse?** You can view the [public example project](/docs/demo) or sign up for a [free account](/cloud) to try Langfuse with your own data. The Hobby plan is completely free and does not require a credit card. **Can I self-host Langfuse for free?** Yes, Langfuse is open source and you can self-host it for free. Use Docker Compose to run Langfuse locally, or use one of the templates to self-host in production on Kubernetes. See the [self-hosting documentation](/self-hosting) to learn more. **What is a billable unit?** A billable unit is any tracing data point you send to Langfuse -- including the trace, observations (spans, events, generations), and scores (evaluations). See [billable units docs](/docs/administration/billable-units) for a detailed explanation. **How does the graduated pricing work?** Graduated pricing means you pay different rates for different volume tiers. The first 100k units are included in paid plans, then you pay $8/100k for 100k--1M, $7/100k for 1M--10M, $6.50/100k for 10M--50M, and $6/100k for 50M+ units. Use the pricing calculator on [langfuse.com/pricing](https://langfuse.com/pricing#pricing-calculator) to estimate your bill. **How can I reduce my Langfuse Cloud bill?** The primary way is to reduce the number of billable units you ingest. See [tips for cutting costs](/faq/all/cutting-costs). With graduated pricing, you automatically get lower rates as your volume increases. **How does Langfuse pricing compare to LangSmith, Braintrust, Arize, and Datadog?** On a representative workload, Langfuse Cloud is cheaper than [LangSmith](/compare/langsmith), [Braintrust](/compare/braintrust), [Arize](/compare/arize-phoenix), and [Datadog Agent Observability](/compare/datadog). Open the [editable pricing comparison sheet](/pricing-comparison-sheet) to fill in your own assumptions and check the numbers for your workload. For product-by-product differences, see the [comparison pages](/compare). Langfuse is also [open source](/why), based on [OpenTelemetry](/integrations/native/opentelemetry) for interoperability, [self-hostable](/self-hosting) at the same scale as Langfuse Cloud, and model- and framework-agnostic. **When do I get billed?** You get one bill each month. The plan fee is charged at the start of the month, and usage is charged at the end of the month. **What are Langfuse Cloud Credits, and how do they affect me?** A Langfuse Cloud Credit is a prepaid unit of credit, equal to one (1) US dollar, to be applied to a customer's use of Langfuse Cloud. Credits are drawn down according to the then-current pricing at [langfuse.com/pricing](/pricing). Langfuse Cloud Credits only apply to customers with a committed spend contract for Langfuse Cloud. If you have questions about your credit balance, drawdown schedule, or committed spend contract, please contact your account team. If you use Langfuse Cloud on a Pay-as-you-Go basis, Langfuse Cloud Credits do not apply to you. **Can I set up alerts on usage fees?** Yes, you can configure [spend alerts](/docs/administration/spend-alerts) to receive email notifications when spending exceeds predefined thresholds. **How can I manage my subscription?** Through the organization settings in Langfuse Cloud or the [Customer Portal](/billing-portal). **Can I purchase Langfuse through AWS Marketplace?** Yes. Enterprise customers with a yearly commitment can bill via AWS Marketplace. [Talk to us](/talk-to-us?deployment=cloud) to request a private offer. Invoice billing is also available. **Can I redline the contracts?** Yes, customized contracts are available for Enterprise customers with a yearly commitment. [Contact sales](/talk-to-us) to discuss your requirements. Default plans are self-serve on standard terms. **Where is the data stored?** Langfuse Cloud is hosted on AWS. Data is stored in the US, EU, Japan, or the HIPAA-compliant US region depending on your selection. See [security documentation](/security) for details. [Ask anything else](/docs/ask-ai) --- ## 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/pricing.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 .