Flexible pricing for
every stage and team.
Developer
One platform for features and agents. Free to start.
Get started freeNo credit card required$0/ mo, forever- Unlimited seatsNo per-seat pricing. Invite your whole team; pricing is based on usage.
- A/B Tests and ExperimentsIncludes 100K experimentation MAU per month at no additional charge.
- 10M logs and 10M traces /moA log is a single log line and a trace is a single span, each ingested, stored, and searchable for one month.
CodeControl:- Unlimited feature flags
- 30 idiomatic SDKs13 client-side, 13 server-side, and 4 edge SDKs.
- 5 service connections and 1K client-side MAU /moA service connection is one server-side SDK connected to one environment for a month. Each unique client-side user or device is one MAU.
- 5K session replays and 5K errors /moA session replay is one recorded user session (a single tab instance); an error is one unique error or exception. Each is stored for one month.
AgentControl:- Configure, evaluate, roll out, and observe your AI end to end
- 5k AI runs/mo includedAn AI Run is generated when you track an LLM request or run an online eval (LLM-as-a-judge).
- 14 days data retentionHow long AgentControl run and eval data stays available.
- Unlimited seats
Foundation
Ship features and agents to production. Scale both without hitting a ceiling.
Pay as you go14-day trial, then pay as you go.
No platform or seat fees.Pay as you goBreak it down
$10per Service Connection / moOne server-side SDK connected to one environment for a month. Serverless and short-lived processes bill fractionally by connection time.$8.33per 1k client-side MAU / moEach unique client-side user or device counts as one monthly active user.$5per 1k executions past 5k / moAn AI run is generated when you track an LLM request or run an online eval (LLM-as-a-judge).Special rates for K8s, Serverless, Python, & RubyBecause these architectures create a high volume of server-side connections, standard per-connection pricing isn't a fair fit. We'll tailor a package to your environment, so the way you run doesn't inflate your bill.Get custom pricingEverything in Developer, plus:- Unlimited projects and environments
- 5 service connections included, pay as you go beyondYour first 5 service connections each month are included. Additional connections bill at $10 each per month.
- Scalable observability usage5K session replays, 5K errors, 10M logs, and 10M traces included each month. Usage beyond that bills as you go.
AgentControl:- Usage-based pricing past 5,000 AI runs/moAn AI Run is generated when you track an LLM request or run an online eval (LLM-as-a-judge).
- 30 days data retentionHow long AgentControl run and eval data stays available.
Enterprise
Full Platform controls and security for engineering teams at scale.
Custom pricingEverything in Foundation, plus:- Advanced user targetingBulk targeting plus large list-based and synced segments.
- Custom roles & teamsFine-grained permissions with custom roles, organized into teams.
- Workflows, scheduling, & approvalsApproval requests, scheduled flag changes, and multi-step release workflows.
- Release automation
- Release Assistant
- SCIM user provisioningAutomated user provisioning and deprovisioning through your identity provider. SSO and SAML are included on every plan.
AgentControl:- Custom number of AI runsAn AI Run is generated when you track an LLM request or run an online eval (LLM-as-a-judge).
- 100 days data retentionHow long AgentControl run and eval data stays available.
Guardian:- Release Monitoring
- Guardrail MetricsMetrics watched during every rollout to catch regressions early.
- Proactive Failure Notifications
- Automatic Pause or Rollback
- Advanced Observability
- Exposure InsightsSee which users and segments were exposed to each release and how it affected them.
- Advanced user targeting
Compare all features
Platform
AI Runs / month
Data / trace retention
Config delivery latency (SLO)
Overage behavior
Add-on AI Run blocks
Service Connections (SCs)
Client-side MAU
Projects & environments
Agent configuration
Prompts & model configs
Prompt Snippets
Tools Library
Agent Graphs
Feature management
Boolean feature flags
Multivariate flags
User / account / device targeting
Segments & percentage rollouts
Flag history
Code references
Flag scheduling
Workflows & approval (flag-level)
Evaluation & quality
Playground
Offline Evals (Datasets + Batch)
Online Evals (LLM-as-judge)
Custom Judges
Datasets
Experimentation
A/B/n testing (configs)
A/B/n testing (feature flags)
Full-stack experimentation
Bayesian and frequentist analysis
CUPED variance reduction
Sequential testing
Sample ratio mismatch (SRM) detection
A/A validity testing
Multi-armed bandits
Confidence and credible interval reporting
Flexible metric design: click, pageview, numeric, conversion, custom event, groups
Warehouse-native integration (Snowflake, Redshift, Databricks, BigQuery and more)
Metrics import: API, integrations, SDK-level
Metric measurement window
Custom SQL metric definitions
Mutual exclusion and layered experiments
Holdouts
Audience definitions and segment targeting
Results filtering by audience attributes
Experiment lifecycle stages
Experiment Approvals
Observability
AI Insights dashboard
LLM Observability (traces)
Data export (AI traces & metrics)
Session Replays
Application Logs
Application Traces
Error monitoring
Automation & release
Agent Optimization
Guarded Rollouts
Adaptive Triggers
Release Monitoring
Guardian only
Guardrail Metrics
Guardian only
Automatic Rollback
Guardian only
Flag Audiences
Guardian only
Safety & guardrails
AI Guardrails & Blocklists
PII Redaction
Integrations
Model providers
Agent frameworks
API Controls
Slack, Microsoft Teams, & Trello
Governance
SSO / SAML
SCIM
Audit Logging
Advanced RBAC / Custom roles
Approvals (governance-level)
Security & Compliance (SOC2 / ISO / HIPAA)
AI & agentic access
MCP Server
Support
Support Response
Support Level
Upgrade Available
Product Uptime
Customer Success Managers
Professional Services
Advisory Sessions
LaunchDarkly Academy
Guided Onboarding Program
LaunchDarkly Certifications
