"A-MINT: An LLM Pipeline for Automated Modeling of iPricings from SaaS Pricing Pages" - Supplementary Material" The aim of this repository is to centralize the work performed by the authors to write the paper: "A-MINT: An LLM Pipeline for Automated Modeling of iPricings from SaaS Pricing Pages" for ICSOC 2025 about A-MINT, an advanced artificial intelligence platform that automates the extraction, analysis, and transformation of SaaS pricing information from natural web pages into structured specifications in iPricing YAML format. The system combines advanced web scraping techniques, natural language processing (NLP), and analysis with constraint satisfaction problem (CSP) algorithms to offer a complete pricing management and intelligence solution. The platform offers a microservices-based architecture with three main components: the A-MINT API (pricing transformation engine, implemented in Python with FastAPI), the Analysis API (CSP-based configuration analysis, implemented in Node.js with TypeScript), and the Choco API (Java Spring Boot service for complementary constraint validation). A modern React-based web frontend provides interactive dashboards, visualization, and pricing file management. Key features include automated extraction of plans, features, and add-ons from SaaS pricing pages; YAML generation and validation; CSP-based configuration space exploration; subscription optimization; and semantic alignment with original content. The system also tracks metrics such as model costs, token usage, processing times, and transformation success rates. Installation is supported via Docker Compose (recommended), with local development possible using Python 3.11+, Node.js 18+, and Java. Once deployed, the platform exposes APIs and a frontend interface for transformation and analysis workflows. Users can transform pricing pages directly via REST endpoints and perform CSP-based optimization and validation tasks. A-MINT enables end-to-end workflows for SaaS pricing management: from intelligent web data extraction, through preprocessing and YAML generation, to mathematical analysis of configurations and automated report generation. It provides a complete environment for research and practice in intelligent pricing, facilitating structured, machine-readable pricing models that can evolve over time. The project is released under the Creative Commons Attribution-ShareAlike 4.0 International License (CC BY-SA 4.0).