Objective: To predict the trend of total expenditure of traditional Chinese medicine in Beijing from 2022—2030 based on the combination model, and to provide data support and references for policy making and adjustment. Methods: ARIMA model and grey GM (1,1) model were used to construct a combined model to forecast the components and total amount of the flow direction of traditional Chinese medicine expense institutions in Beijing. Results: The fitting accuracy of the combined model is obviously better than that of GM (1,1) model and ARIMA model respectively. According to the forecast results, the total cost of traditional Chinese medicine in Beijing increased from 82.623 billion yuan in 2022 to 144.713 billion yuan in 2030, with an average annual growth rate of 7.26% , and the flow of institutions was optimized significantly. Conclusion: The use of combination models can be applied to explore the forecasting accuracy for cost forecasting research. Public health emergencies have a great impact on the cost of traditional Chinese medicine. The prediction research results should be viewed reasonably and the prediction model should be continuously optimized according to the changes of the actual situation.