The efficiency of freight transportation plays a crucial role in minimizing energy consumption and promoting sustainability within the logistics sector. This study explores the application of artificial intelligence (AI) to enhance the freight distribution process; aiming to reduce energy consumption per ton-kilometer. The primary goal is to leverage AI algorithms to improve freight capacity utilization and lower operational energy costs. To accomplish this goal, a machine learning-based optimization framework was developed, incorporating real-time analysis of logistics data, predictive modeling, and heuristic techniques. Historical freight data was examined to uncover patterns and limitations in the distribution process, leading to the creation of an adaptive optimization model. This model was evaluated under both simulated and real-world conditions, allowing for a comparison with traditional methods.  The findings revealed that the AI-driven approach increased freight capacity efficiency by an average of 15% and decreased energy consumption per ton-kilometer by 12%. Additionally, the system demonstrated scalability and adaptability across various cargo types and operational constraints. In short, integrating AI into freight distribution optimization has significantly transformed logistics operations, offering an efficient and scalable solution to modern transportation challenges. Future research will aim to integrate these models with Internet of Things (IoT) technologies to enable real-time adaptation and further enhance decision-making processes.