Bengaluru, August 2026: Bengaluru-based fintech company Razorpay has launched Vulcan, a transformer-based AI foundation model built specifically for the payments ecosystem. The company said the model is designed to improve payment success rates, fraud detection, payment routing, risk assessment and checkout personalisation.
Vulcan has been trained on nearly 4 billion payments and 3 trillion data points, analysing around 3,000 signals per transaction. Unlike general-purpose AI models, Vulcan is designed to understand payment behaviour across merchants, payment instruments, issuing banks and payment gateways.
The model has been developed using technology and infrastructure from NVIDIA and AWS, with Amazon SageMaker supporting its training and deployment.
Razorpay said early components of Vulcan have already been tested on live transactions, with companies including Blinkit, Bachatt and redBus using some of its capabilities. Early deployments have reportedly delivered an 8–10% improvement in payment success rates.
The company also said Vulcan detected eight times more international card fraud and identified five times more fraudulent or disputed transactions without increasing the number of alerts.
On its Magic Checkout platform, the technology helped 40% more shoppers see their preferred UPI app, contributing to an additional 1–2 lakh purchases per month, according to Razorpay.
Vulcan can analyse transaction signals to identify the payment route most likely to succeed, detect fraud patterns, assess risks associated with cash-on-delivery orders and recommend suitable payment methods.
Also Read: Praful Rajpopat Appointed Chief Credit Officer at Fedfina
Razorpay CEO and Co-founder Harshil Mathur said Vulcan is designed to continuously improve as it processes more payment data. The company clarified that Vulcan is not an LLM like ChatGPT, but a payments-focused foundation model built to identify patterns in how money moves through its network.
Razorpay plans to expand Vulcan across authentication, routing, fraud detection and lending as digital payments continue to grow in India.
