Smart freight platforms are emerging as a key component of the new sustainable and smart mobility paradigm. These platforms enable efficient and flexible matching of freight demand and supply, reducing costs and environmental impacts. However, the matching process is subject to various uncertainties, such as weather, traffic, and truck failures, which can affect the performance and reliability of the platform and provided services. In this study, we develop a two-stage stochastic optimization model for matching smart freight platform that considers these uncertainties. The model aims to maximize the matching rate of the platform while satisfying the service level requirements of the customers and minimizing the environmental impacts considering the consolidation. We apply the model to the case of Montreal, Canada, using a simulated data set that reflects the characteristics of the city’s freight market. The results show that the model can improve the matching quality and robustness of the platform under different scenarios of uncertainty.