A discrete-time predictive dynamic user-optimal departure time/route choice problem has been formulated and solved with the nested diagonalization method by Chen, H.K., Hsueh, C.F. (1998a. A discrete-time dynamic user-optimal departure time/route choice model. Transportation Engineering, ASCE 124 (3), 246–254). That model did not impose constraints on either departure times at origin or arrival times at destination, which are typically required for regular work trips. However, for better representing practical situations, the time-window constraints associated with both the departure times and arrival times, along with link capacity side constraints, need to be incorporated into the aforementioned model. The resulting dynamic capacitated user-optimal departure time/route choice model with time-window can appropriately model the queuing delay associated with each capacitated time–space link and also can properly differentiate off-peak and peak phenomena within the analysis period. A numerical example is provided for demonstration.