The transformation of land use induced by human activities has significantly altered the structure and functionality of ecosystems, thereby impacting the overall level of ecosystem services. The assessment of ecosystem services value serves (ESV) is crucial for the rational allocation of natural resources and environmental protection, helping policymakers and stakeholders understand the trade-offs associated with different land use decisions and promotes strategies that can enhance or maintain the benefits ecosystems provide to human well-being. Focusing on the Beijing metropolitan area, this study conducts a comprehensive analysis of the spatial distribution and temporal variations in the overall ecosystem services value at the 1 km×1 km grid level, leveraging data from three phases of remote sensing image interpretation (2003, 2010, and 2022). Employing methodologies such as the equivalent factor method and spatial autocorrelation analysis, the research explores the impact of the two rounds of citywide master plans on ESV. Furthermore, the geo-detector, a spatial analysis tool is applied to explore the driving factors behind the spatial heterogeneity of ESV. The results show that: (1) Throughout the study period, the characteristics of overall ESV changes in the city corresponded to variations in non-construction land components, exhibiting a trend of initial decline followed by an increase. Specifically, the total ESV increased by 10.946 billion yuan, indicating a substantial enhancement in the provision of ecosystem services. The expansion of forested and aquatic areas emerged as a pivotal factor contributing to the augmentation of ecosystem service value. (2) Over time, the values of the four predominant types of ecosystem services show a gradual decrease in the following order: regulatory services, supporting services, provisioning services, and cultural services. Consequently, regulatory services emerge as the dominant function of the ecosystem. (3) Spatially, ESV exhibits a northwest-high, southeast-low pattern, demonstrating positive correlation and spatial aggregation throughout the city. Local patterns show high-high and low-low aggregation, with ESV hotspots primarily concentrat in extensive wetland areas, while cold spots gradually contract toward the city center. This spatial distribution highlights the importance of preserving and enhancing green spaces and water bodies in urban planning to maintain and boost ecosystem services. (4) The spatial heterogeneity of ESV is influenced by both natural geographical and socio-economic factors, with temperature exerting the most significant impact. The synergistic effects between these factors enhance the explanatory power for ESV. This study unveils the temporal and spatial patterns of changes in ecosystem services during urban land use transformations and their driving forces, providing crucial insights for sustainable urban development. It also offers management recommendations for enhancing ESV, which are vital for the sustainable utilization and management of natural resources.