This chapter provides an overview of the Optimal Transport (OT) framework and its potential applications in causal inference. It begins by addressing the limitations of traditional methods like Maximum Likelihood Estimation (MLE) and Kullback-Leibler (KL) divergence, especially in high-dimensional settings and generative models with non-overlapping supports. The chapter then delves into the OT problem, exploring both Monge’s original formulation and Kantorovich’s dual formulation, and how these lead to the Wasserstein distance. Computational challenges are tackled through the introduction of entropy regularization and the Sinkhorn algorithm, which offers a scalable and efficient solution to OT problems. The chapter further explores the application of OT in causal inference, particularly within the Difference in Differences (DiD) framework, and discusses multivariate extensions of OT-based methods. Through these discussions, the chapter highlights the versatility and power of OT as a tool for both theoretical and applied research, providing insights into its role in optimizing resource allocation, improving machine learning models, and advancing causal analysis.