In order to improve the economic benefit of AC / DC hybrid microgrid, an optimal operation method based on real-time price mechanism is proposed. Firstly the optimal operation model is built according to the structure and electrical characteristics of AC/DC microgrid. Secondly according to load composition, the load level response model to real-time price based on load classification is constructed. The proposed day-ahead scheduling model is used considering the real time price as the control variables, and the real-time price on next day and the day-ahead scheduling of AC/DC microgrid can be given by this model. The proposed model is solved by chaotic particle swarm optimization algorithm. Finally through an example to verify the method proposed in this paper can improve the scenery absorptive rate, increase the AC DC hybrid microgrid revenue and reduce user’s average electricity costs. This work is supported by National High-tech R & D Program of China (863 Program) (No. 2015AA050104) and National Natural Science Foundation of China (No. 51577068).