Razorpay launches Vulcan AI model with NVIDIA, AWS to boost payment success, fraud detection

Razorpay has launched Vulcan, an AI foundation model designed specifically for payments, as the fintech company looks to improve payment success rates, fraud detection and checkout experiences. Built with NVIDIA and AWS, the transformer-based model has been trained on nearly 3 trillion data points across 4 billion payments.

Razorpay said early components of Vulcan have delivered an 8-10% improvement in payment success rates. The company also said the technology detected eight times more international card fraud and identified five times more fraudulent or disputed transactions without increasing the number of alerts. On Razorpay Magic Checkout, 40% more shoppers are now seeing their preferred UPI app, helping complete an additional 1-2 lakh purchases every month.

The model is designed to act as a single intelligence layer across payment routing, fraud, risk and checkout, replacing separate machine-learning models for individual functions. It learns from roughly 3,000 signals per transaction and evaluates payment routes in real time to identify the route most likely to succeed.

Razorpay said the model is already being used in live payment environments by customers including Blinkit, Bachatt and redBus. An internal study covering 1.5 million shoppers and more than 51,000 businesses found similar payment friction across metros and smaller towns, the company said.

Vulcan can also detect fraud across Razorpay’s network, flag potentially risky Cash on Delivery orders and recommend the payment method most likely to work for a particular customer.

Harshil Mathur, CEO and Founder of Razorpay, said, “India’s appetite for digital payments is real, but it isn’t universal yet - for a large part of the country, going digital still comes down to one thing: does it work, every single time? That’s the customer we built this for: the one still deciding whether to trust a screen over cash in hand. An AI-led payments foundation model doesn’t just solve today’s problem and stop there. Every payment teaches the system something that makes the next payment better. That’s what makes this feel less like a product launch, and more like the starting point for how payments in India keep getting better on their own, for years to come.”

The model is not an LLM such as ChatGPT. Razorpay describes it as a foundation model trained specifically on payments data to understand patterns in the movement of money. NVIDIA GPUs were used to train and run the model, while AWS infrastructure, including Amazon SageMaker, supports its development, training and deployment.

Pahal Patangia, Head of Global Industry Business Development and Payments, NVIDIA, said, “India’s rapidly evolving digital economy is creating an opportunity to make payments more intelligent, reliable, and secure. NVIDIA’s work with Razorpay in partnership with AWS on AI payments foundation models has opened up a new frontier, turning complex payments data into real-time contextual intelligence. This has a proprietary and purpose-built semantic AI layer that can help advance the next generation of digital financial services.”

Kiran Jagannath, Head of FSI and Conglomerates, AWS India and South Asia, said, “Razorpay is reimagining payments intelligence at India scale with an AI Foundation Model - built on Amazon SageMaker - that consolidates billions of transaction insights into a single, continuously learning intelligence layer, replacing fragmented ML models with unified AI that delivers higher payment success rates, rapid iteration, and enterprise-grade security for mission-critical payment flows. As India’s digital economy grows, we are excited to power the AI infrastructure behind payments that simply work for every Indian.”

Razorpay said it eventually wants the model to power payment decisions ranging from authentication and routing to fraud and lending. The company cited India’s digital e-commerce market, which it projects will reach $350 billion by 2030, as the broader market opportunity for the technology.