Introduction: Prevention of the health risk of amateur marathon runners is of great significance for the sustainable development of marathon. To reduce the psychological burden of amateur marathon runners and improve the participation experience, the current study used the health belief model to study the relationship among health beliefs, attitude to preventative behavior, self-efficacy, and health values of amateur marathon runners. Methods: A total of 342 data were collected, and using the PROCESS (analytical procedures developed for mediating and moderating effects tests based on SPSS and SAS). A series of multiple linear regression models were established to study the relationship between variables, and the bootstrap confidence interval was selected to test the mediating and moderating effect. Results: The results showed that perceived health threat (b = 0.463, p <0.05), health behavior expectations (b = 0.373, p <0.001), self-efficacy (b = 0.322, p <0.001), and behavioral attitudes (b = 0.230, p <0.001) can be regarded as antecedent variables for predicting preventative behaviors. In addition, the results also show that health behavior expectations, self-efficacy, and behavioral attitudes play chain-mediating role between perceived health threat and preventative behaviors. Health values appear to play a moderating role in the direct/indirect effects of perceived health threat on preventive behavior through a number of mediating variables. Discussion: This study emphasizes that the amateur marathon runners must improve their health concept and take effective preventive measures before participating in the competition. According to this research, it is the responsibility of the event parties, public health officials and relevant departments of the host city to provide rich health information and risk education to amateur marathon runners. More public service advertisements or educational materials are needed to be placed on runners to enhance their awareness of the necessity and importance of taking preventive measures.