Stripe Radar
Stripe Radar is Stripe's machine learning fraud product for businesses that take payments online and for platforms and marketplaces with connected accounts. It scores every payment in real time with models trained on more than 70 trillion data points from the Stripe network, which processed $1.9 trillion in payments in 2025, and it runs by default on Stripe payments. An API also scores payments, accounts and customers for businesses that process elsewhere, so a team can keep its existing processor.
Coverage runs across the customer lifecycle: card testing and transaction fraud at payment, risky accounts and merchant monitoring at onboarding, and abuse such as multiple accounts, free trials, bots and account sharing. A business can allow or block a payment, trigger Adaptive 3D Secure or send it to manual review. Paid plans add risk scores from 0 to 99, custom rules backtested on past payments, risk preferences and Radar Assistant, and Pro adds dynamic risk thresholds. Dispute prevention draws on Verifi and Ethoca.
Radar Lite is included with standard Stripe card pricing. Radar Standard, Plus and Pro cost $0.05, $0.07 and $0.09 per screened transaction pay as you go, or start at $10, $14 and $20 a month with 200 transactions included. Platform plans start at $20, $44 and $70 a month, and enterprise access is quoted.
Stripe reports a 32% average reduction in fraud. FreshBooks blocked more than 300 fraudulent accounts from onboarding in three months, Anthropic saw 83% fewer legitimate transactions wrongly blocked, and DoorDash cut chargeback costs by 10% on payments processed outside Stripe.
Capability Axes
Capability grades
15 of 15 axes rated · 14 graded A or B
The learned risk signal is what Radar sells. Adaptive models trained on the Stripe network score each payment, account and customer from payment signals and outcomes such as fraud that merchants report, and the same signal is sold on its own to businesses that process elsewhere. Custom rules let operators layer their own policies on top.
Each payment can be allowed, blocked, sent to 3D Secure or routed to a review queue. Businesses on Plus or Pro write rules, backtest them against earlier payments and set risk preferences, and Pro adds dynamic risk thresholds. Reviewers inspect queued payments in the Dashboard where the payment method supports it, and for connected account decisions the platform must give the affected account a route to human review.
Paid plans show a 0 to 99 risk score beside the highest, elevated or normal risk level, and custom rules can be backtested on past payments before they go live. Stripe evaluates model changes on precision, recall, authorization and block rates, in aggregate and per merchant, and monitors performance after release as fraud patterns shift. A version history for production models and an independent benchmark by payment method are not published.
FreshBooks blocked more than 300 fraudulent accounts from onboarding onto its payments service in three months, combining merchant information with transaction monitoring. Anthropic saw an 83% reduction in legitimate transactions incorrectly blocked, and DoorDash cut chargeback costs by 10% on payments processed outside Stripe, by Stripe's account. Across its users, Stripe reports a 32% average reduction in fraud.
Network learning is the design: Stripe pools transaction signals across its merchant network, so one business's activity helps score payments for others. The Privacy Center limits that use to preventing fraud and improving payment performance, not judging an individual's character or creditworthiness, and uses aggregated or deidentified information so a business cannot identify another business's customers. The Radar terms require merchants to delete certain Radar data at termination or on request. Retention periods for the training data are not stated.
A data processing agreement sets Stripe's processor duties, safeguards and transfer terms, and Stripe holds CBPR and PRP privacy certifications and participates in the EU-US, UK and Swiss data privacy frameworks. The Radar terms require businesses to tell their customers that Stripe collects device characteristics and customer activity indicators for fraud detection, and the Privacy Center explains how Stripe uses personal information in its own fraud models.
A SOC 3 report downloads freely from Stripe's security page. Coalfire Controls examined the Stripe Global Payments and Revenue and Finance Automation system for October 2024 to September 2025 against the security, availability and confidentiality criteria, and the system description names Radar in scope. SOC 1 and SOC 2 Type II reports are produced annually and come through the Dashboard or on request, and Stripe is certified as a PCI Service Provider Level 1.
Stripe's terms present Radar as a risk service, leaving the business to apply its own decision rules and to handle the payments it accepts. Stripe Payments Company holds state money transmitter licenses for its money transmission, and those licenses sit with that entity and activity rather than with the fraud product. Radar for Platforms extends the same risk information to platforms deciding on their connected accounts.
Before a model ships, Stripe tests it on authorization, false positive and block rates across all merchants and across subsets of them, and adjusts the model or policy for groups of merchants when a change would shift their outcomes badly. That is a named process for catching regressions across commerce segments. How block rates fall across the cardholders behind those payments is not reported.
Platforms using Radar must let a connected account seek human review when Radar informed a decision about it, and must pass Stripe any information suggesting the output was wrong, which gives the affected business a real correction route. For payments, the merchant stays responsible for what it accepts, fraud disputes included. Chargeback Protection pays only on protected charges where Stripe has activated it, and standard screening carries no reimbursement for a wrong score.
Models are built and trained by Stripe on activity across its services, Financial Connections data, third party providers and public sources, and the Privacy Center separates the transaction fraud models behind Radar from the authorization models in Stripe Issuing. Radar runs specialized models for some payment methods, and Verifi and Ethoca supply dispute prevention signals. The third party data providers behind training, and the infrastructure that runs each plan's models, are not named.
On Stripe, Radar attaches to Payments, Checkout, Billing and Connect through objects such as charges and payment intents and needs no extra integration. Businesses on another processor send payment, account and customer signals to the Radar API and act on the results in their own stack. Dispute prevention connects to Verifi and Ethoca, and Smart Disputes assembles and submits evidence on the merchant's behalf.
The service runs hosted inside Stripe's payments infrastructure and through an API for businesses that process elsewhere, with rules, reviews and analytics in the Dashboard. Card data sits in a separate, isolated AWS environment, and the data processing agreement covers international transfers. A residency commitment for Radar scoring and model data, a private cloud option or a version that runs in customer infrastructure is not stated.
The entry tier, Radar Lite, is included with standard Stripe payments pricing. Standard, Plus and Pro cost $0.05, $0.07 and $0.09 per screened transaction pay as you go, with Pro adding $0.005 per abuse event, or start at $10, $14 and $20 a month with 200 screened transactions included and the same per transaction rate beyond. Platform plans start at $20, $44 and $70 a month, and enterprise access to Radar's signals for payments processed elsewhere is quoted.
Separate plans serve businesses that take payments and platforms and marketplaces with connected accounts, where Radar adds fraud scores for every account, automatic reserves and payout restrictions, and the service can score payments processed by another provider. FreshBooks screens businesses joining its payments service, DoorDash tested it on payments outside Stripe, and Anthropic uses it on its own payments. Subscription, usage based and travel businesses get abuse controls for trials, account sharing and pay as you go usage.
Alternatives to Stripe Radar
Other products that do the same kind of work as Stripe Radar, and what each one does.
Chargeflow automates chargeback prevention and recovery for ecommerce and SaaS merchants and for the payment platforms that serve them, with more than 20,000 merchants in its network across 90 countries.
Coris supplies merchant risk infrastructure to the parties that underwrite merchants rather than to merchants themselves, covering software platforms with embedded payments, independent sales organizations, payment facilitators, acquiring and sponsor banks, marketplaces and lenders.
Disputifier is a chargeback defense platform for ecommerce merchants, ISOs, CRMs, payment service providers and enterprises running thousands of merchant IDs.
Forter decides in real time whether to trust the person or AI agent behind an online purchase, login or return. Retailers, marketplaces and travel brands use it to approve more good orders and stop fraud, account takeover and policy abuse.
G2 Risk Solutions sells merchant risk intelligence to banks, merchant acquirers, payment providers and marketplaces, and since its combination with EverC, announced in August 2025, it sells the former EverC products for detecting high risk sellers, transaction laundering and illicit or…
NoFraud sells full service ecommerce fraud screening to small and mid sized merchants, with a Shopify centered distribution model and commercial terms a merchant can test without paying.
Pricing
Vendor-published figures are labeled as such. Figures labeled “Estimated” are derived from third-party sources and have not been confirmed by the vendor.
| Entry Price | Pricing Basis | Data Protection Terms | Implementation | Source |
|---|---|---|---|---|
|
Radar Lite has no added charge on standard Stripe payments pricing. Paid plans start at $10 per month.
$10 baseline
|
Radar Standard, Plus and Pro cost $0.05, $0.07 and $0.09 per screened transaction pay as you go, and Pro adds $0.005 per abuse event. Subscriptions start at $10, $14 and $20 a month with 200 screened transactions included and the same per transaction rate beyond. Platform plans start at $20, $44 and $70 a month. Enterprise pricing, including risk signals for payments processed elsewhere, is quoted. | Stripe's Radar terms and data processing agreement cover use and sharing of data. The published plans do not list distinct data protection terms. | Stripe offers an integration through its payments products and an interface for other processors. Enterprise integration support is quoted. | Vendor Published |
Radar Lite covers card fraud and card testing, with fraud alerts, at no added charge on standard Stripe payments pricing. Plus adds risk scores, custom rules with backtesting, manual reviews, risk preferences, Adaptive 3D Secure, Smart Refunds and Radar Assistant. Pro adds dynamic risk thresholds and abuse screening for free trials, bots, multiple accounts, account sharing and pay as you go usage.