Considering that the construction industry represents a substantial share of energy consumption and greenhouse gas (GHG) emissions worldwide, it is evident that sustainable construction will be bolstered by the use of emerging technologies. This research seeks to demonstrate that large language models (LLMs) will improve energy use efficiency and material effectiveness in the process of sustainable construction. LLMs are inherently multi-objective optimizations as their capacity to process information exceeds that of even the largest databanks. Therefore, compilations of designs that would otherwise be limited to a data set for a finite construction documentation goal can be assessed for energy, materials, financing, and code requirements for an all-encompassing accepted result. Results determined that LLMs can dictate energy-efficient designs based on historical usage and anticipated trends, recommend sustainable materials based on low embodied carbon number but high operational benefits, and generate revenue for firms based on ease of obtaining Leadership in Energy and Environmental Design (LEED) and Building Research Establishment Environmental Assessment Method (BREEAM) certification from project kick-off due to prescriptive recommendations generated in the beginning. LEED-related case studies show nearly 50% energy efficiency savings and nearly 45 million kg reductions for carbon footprint. Limitations include but are not limited to data availability, increased construction costs, and lack of interpretability. Ultimately, integrating LLMs into the sustainable construction process for the built environment serves to alleviate pressures brought to light by the climate crisis and the need for effective construction integration. Future studies should be undertaken to assess potential dependence for ultimate effectiveness.