This paper presents the development of models that describe the surface-generation process for microendmilling. The surface-generation models for the sidewall and floor surfaces consist of deterministic and stochastic models. In the sidewall surface-generation model, the deterministic model characterizes the surface topography generated from the relative motion between the major cutting edge and the workpiece material. The model includes the effects of the process kinematics, dynamics, tool edge serration, and process faults (e.g., tool tip runout). The stochastic model predicts the increased surface roughness generated from ploughing due to the significant tool edge radius effect. In the floor surface-generation model, the deterministic model characterizes the three-dimensional surface topography over the entire floor surface and considers the effects of the minimum chip thickness, the elastic recovery, and the transverse vibration. The variation of the ploughing amount across the swept arc of the cutter due to the varying chip load conditions is considered in the stochastic model.