Pricing

Get started on the Hobby plan for free. No credit card required.

Langfuse CloudSelf-hosted
Hobby
Get started, no credit card required. Great for hobby projects and POCs.
Free
Trusted by:
40,000+ builders
  • All platform features (with limits)
  • 50k units / month included
  • 30 days data access
  • 2 users
  • Community support (Discord & GitHub)
Unlimited Users
Core
For production projects. Longer data retention and unlimited users.
$59/ month
Startup? Get 50% off
Trusted by:
Kombo
Draftbit
  • Everything in Hobby
  • 100k units / month included, additional: $8/100k units. Lower with volume ()
  • 90 days data access
  • Unlimited users
  • Unlimited evaluators
  • Support via Email/Chat
Unlimited Users
Pro
For scaling projects. Unlimited history, high rate limits, all features.
$199/ month
Startup? Get 50% off
Trusted by:
Twilio
SumUp
  • Everything in Core
  • 100k units / month included, additional: $8/100k units. Lower with volume ()
  • Unlimited data access
  • Unlimited annotation queues
  • High rate limits
  • SOC2 & ISO27001 reports, BAA available (HIPAA)
  • Support via Slack
+ optional
Teams Add-on$300/mo
  • Enterprise SSO (e.g. Okta)
  • SSO enforcement
  • Fine-grained RBAC
  • Data retention management
Enterprise
Enterprise-grade support and security features.
Custom
Trusted by:
Khan Academy
  • Everything in Pro and Teams add-on
  • Custom rate limits
  • Uptime SLA
  • Support SLA
  • Custom Terms & DPA
  • Dedicated support engineer
  • Architecture reviews
  • Billing via AWS Marketplace
  • Billing via Invoice
Startup discounts available|Academic & research benefits

Feature comparison

Hobby

Get started, no credit card required. Great for hobby projects and POCs.

LLM Application & Agent Tracing
Traces and Graphs (Agents)
Session Tracking (Chats/Threads)
User Tracking
Token and Cost Tracking
Native Frameworks Integrations
SDKs (Python, JavaScript)
OpenTelemetry (Java, Go, custom)
Proxy-based Logging (via LiteLLM)
Custom via API
Included usage
50k units
Additional usage
Multi-modal
Free while in beta
Access to historical data
30 days
Ingestion throughput
1,000 requests / min
Prompt Management
Prompt Versioning
Prompt Fetching
Unlimited
Prompt Release Management
Prompt Composability
Prompt Caching (server and client)
Playground
Prompt Experiments
Protected Deployment Labels
Evaluation (online and offline)
Datasets
Custom Experiments (via SDK)
Evaluation Scores (custom)
User Feedback Tracking
Human Annotation
Human Annotation Queues
1 queue
External Evaluation Pipelines
LLM-as-judge evaluators
1 evaluator
Collaboration
Projects
Unlimited
Users
2
API
Extensive Public API
Rate limit (general API routes)
30 requests / min
Rate limit (datasets api)
100 requests / min
Rate limit (metrics api)
100 requests / day
SLA
Exports
Batch Export via UI
PostHog Integration
Scheduled Batch Export to Blob Storage
Support
Ask AI
Community (GitHub, Discord)
Chat & Email
Private Slack/Discord channel
Dedicated Support Engineer
Support SLA
Architectural guidance
Security
Data region
US or EU
Data masking
SSO via Google, AzureAD, GitHub
Organization-level RBAC
Enterprise SSO (e.g. Okta, AzureAD/EntraID)
SSO enforcement
Project-level RBAC
Data retention management
Audit Logs
Billing
Subscription management
Payment methods
Contract duration
Billing via AWS Marketplace
Compliance
Contracts
Standard T&Cs
Data processing agreement (GDPR)
SOC2 Type II & ISO27001 reports
HIPAA compliance
InfoSec/legal reviews

Core

For production projects. Longer data retention and unlimited users.

LLM Application & Agent Tracing
Traces and Graphs (Agents)
Session Tracking (Chats/Threads)
User Tracking
Token and Cost Tracking
Native Frameworks Integrations
SDKs (Python, JavaScript)
OpenTelemetry (Java, Go, custom)
Proxy-based Logging (via LiteLLM)
Custom via API
Included usage
100k units
Additional usage
$8/100k units. Lower with volume ()
Multi-modal
Free while in beta
Access to historical data
90 days
Ingestion throughput
4,000 requests / min
Prompt Management
Prompt Versioning
Prompt Fetching
Unlimited
Prompt Release Management
Prompt Composability
Prompt Caching (server and client)
Playground
Prompt Experiments
Protected Deployment Labels
Evaluation (online and offline)
Datasets
Custom Experiments (via SDK)
Evaluation Scores (custom)
User Feedback Tracking
Human Annotation
Human Annotation Queues
3 queues
External Evaluation Pipelines
LLM-as-judge evaluators
Collaboration
Projects
Unlimited
Users
Unlimited
API
Extensive Public API
Rate limit (general API routes)
100 requests / min
Rate limit (datasets api)
200 requests / min
Rate limit (metrics api)
200 requests / day
SLA
Exports
Batch Export via UI
PostHog Integration
Scheduled Batch Export to Blob Storage
Support
Ask AI
Community (GitHub, Discord)
Chat & Email
Private Slack/Discord channel
Dedicated Support Engineer
Support SLA
Architectural guidance
Security
Data region
US or EU
Data masking
SSO via Google, AzureAD, GitHub
Organization-level RBAC
Enterprise SSO (e.g. Okta, AzureAD/EntraID)
SSO enforcement
Project-level RBAC
Data retention management
Audit Logs
Billing
Subscription management
Self-serve
Payment methods
Credit card
Contract duration
Monthly
Billing via AWS Marketplace
Compliance
Contracts
Standard T&Cs & DPA
Data processing agreement (GDPR)
SOC2 Type II & ISO27001 reports
HIPAA compliance
InfoSec/legal reviews

Pro

For scaling projects. Unlimited history, high rate limits, all features.

LLM Application & Agent Tracing
Traces and Graphs (Agents)
Session Tracking (Chats/Threads)
User Tracking
Token and Cost Tracking
Native Frameworks Integrations
SDKs (Python, JavaScript)
OpenTelemetry (Java, Go, custom)
Proxy-based Logging (via LiteLLM)
Custom via API
Included usage
100k units
Additional usage
$8/100k units. Lower with volume ()
Multi-modal
Free while in beta
Access to historical data
Unlimited
Ingestion throughput
20,000 requests / min
Prompt Management
Prompt Versioning
Prompt Fetching
Unlimited
Prompt Release Management
Prompt Composability
Prompt Caching (server and client)
Playground
Prompt Experiments
Protected Deployment Labels
Teams add-on
Evaluation (online and offline)
Datasets
Custom Experiments (via SDK)
Evaluation Scores (custom)
User Feedback Tracking
Human Annotation
Human Annotation Queues
External Evaluation Pipelines
LLM-as-judge evaluators
Collaboration
Projects
Unlimited
Users
Unlimited
API
Extensive Public API
Rate limit (general API routes)
1,000 requests / min
Rate limit (datasets api)
1,000 requests / min
Rate limit (metrics api)
2000 requests / day
SLA
Exports
Batch Export via UI
PostHog Integration
Scheduled Batch Export to Blob Storage
Teams add-on
Support
Ask AI
Community (GitHub, Discord)
Chat & Email
Private Slack/Discord channel
Dedicated Support Engineer
Support SLA
Architectural guidance
Security
Data region
US or EU
Data masking
SSO via Google, AzureAD, GitHub
Organization-level RBAC
Enterprise SSO (e.g. Okta, AzureAD/EntraID)
Teams add-on
SSO enforcement
Teams add-on
Project-level RBAC
Teams add-on
Data retention management
Teams add-on
Audit Logs
Billing
Subscription management
Self-serve
Payment methods
Credit card
Contract duration
Monthly
Billing via AWS Marketplace
Compliance
Contracts
Standard T&Cs & DPA
Data processing agreement (GDPR)
SOC2 Type II & ISO27001 reports
HIPAA compliance
InfoSec/legal reviews

Enterprise

Enterprise-grade support and security features.

LLM Application & Agent Tracing
Traces and Graphs (Agents)
Session Tracking (Chats/Threads)
User Tracking
Token and Cost Tracking
Native Frameworks Integrations
SDKs (Python, JavaScript)
OpenTelemetry (Java, Go, custom)
Proxy-based Logging (via LiteLLM)
Custom via API
Included usage
Custom
Additional usage
Custom
Multi-modal
Free while in beta
Access to historical data
Unlimited
Ingestion throughput
Custom
Prompt Management
Prompt Versioning
Prompt Fetching
Unlimited
Prompt Release Management
Prompt Composability
Prompt Caching (server and client)
Playground
Prompt Experiments
Protected Deployment Labels
Evaluation (online and offline)
Datasets
Custom Experiments (via SDK)
Evaluation Scores (custom)
User Feedback Tracking
Human Annotation
Human Annotation Queues
External Evaluation Pipelines
LLM-as-judge evaluators
Collaboration
Projects
Unlimited
Users
Unlimited
API
Extensive Public API
Rate limit (general API routes)
Custom
Rate limit (datasets api)
Custom
Rate limit (metrics api)
Custom
SLA
Exports
Batch Export via UI
PostHog Integration
Scheduled Batch Export to Blob Storage
Support
Ask AI
Community (GitHub, Discord)
Chat & Email
Private Slack/Discord channel
Dedicated Support Engineer
Support SLA
Architectural guidance
Security
Data region
US or EU
Data masking
SSO via Google, AzureAD, GitHub
Organization-level RBAC
Enterprise SSO (e.g. Okta, AzureAD/EntraID)
SSO enforcement
Project-level RBAC
Data retention management
Audit Logs
Billing
Subscription management
Sales
Payment methods
Credit card, Invoice
Contract duration
Custom
Billing via AWS Marketplace
Compliance
Contracts
Custom
Data processing agreement (GDPR)
SOC2 Type II & ISO27001 reports
HIPAA compliance
InfoSec/legal reviews

Discounts

Early-stage startups
50% off, first year
Learn more and apply
Research / Students
Up to 100% off, limits apply
Learn more and apply
Open-source projects
USD 300 in credits / month, first year

Reach out to [email protected] to apply for a discount. We want all startups, educational users, non-profits and open source projects to build with Langfuse and are happy to work with you to make that happen.

Frequently asked questions

Was this page helpful?
Support