In order to explore whether time-dependent fare strategy can be introduced into the subway operation of type I big cities to alleviate the severe passenger flow congestion brought by holidays, the survey data of Nanchang subway respondents is used to analyze the travel time choice behavior of subway passengers in type I big cities. SP survey method was used to collect data on respondents’travel time choice preferences under the influence of three scheme variables: travel time change, fare and congestion level. Conditional Logit model and mixed Logit model were used to estimate the variable coefficients of utility function. The results show that the change length of travel time has a significant and negative effect on travel time choice behavior, and the fare level has a significant and positive effect on travel time choice behavior. Compared with the change length of travel time and the congestion level, the fare has a greater impact on the travel time choice behavior, and the respondents are more willing to choose the pre-peak period. The research can provide decision-making reference for relieving passenger flow congestion of subway in type I big cities during holidays.