The SaaS paradigm has revolutionized software distribution by offering flexible pricing options, but its rapid growth has introduced complexity for DevOps teams, who still manage and evolve pricing structures manually. This process is time-consuming and error-prone, lacking automated tools for efficient pricing analysis, optimization, and scaling. We propose leveraging intelligent pricing (iPricing)-dynamic, machine-readable pricing models-to address these challenges. iPricing enables competitive analysis, streamlines decision-making, and adapts pricing to market changes, enhancing efficiency and accuracy. Our LLM-driven approach automates the transformation of static HTML pricing into iPricing, improving consistency and reducing human error. The implementation, AI4Pricing, includes an Information Extractor using web scraping and LLMs to identify and extract key pricing elements-plans, features, usage limits, and add-ons-from SaaS websites. Validation on a dataset of up to 30 distinct commercial SaaS shows effective extraction across all steps, though challenges with hallucinations, complex structures, and dynamic content persist. This work underscores the potential of automating iPricing transformation to streamline SaaS pricing management, improving consistency and scalability. Future research will focus on refining extraction and expanding adaptability to a wider range of SaaS websites.