Although surgery is considered the first choice of treatment for patients diagnosed with tracheal cancer, the prediction of overall survival (OS) in patients undergoing surgical intervention is poor. To address this issue, we developed a nomogram that combined a risk classification system to estimate the OS of patients with tracheal cancer who underwent surgical intervention. A total of 525 qualified patients were selected from the surveillance, epidemiology, and end results database between 1975 and 2018 and were randomly divided into training and validation cohorts (7:3). The parameters of independent prognostic ability were determined using Cox regression analysis, and a nomogram was formed. The predictive ability of the nomogram was tested using the area under the curve of receiver operating characteristic curves and calibration curves. Survival curves were assessed between the different risk classification groups using the Kaplan–Meier method. The results indicated that Age, stage, histology, and tumor size were independent prognostic factors and were included in the predictive model. The calibration plots demonstrated good agreement between the nomogram prediction and actual observation for 24- and 36-month OS. The receiver operating characteristic curves suggested that the predictive model had good discrimination ability, with the area under the curves (training group 0.817, 0.785, and 0.801, respectively) and validation group (0.744, 0.794, and 0.822, respectively). Furthermore, the low-risk group had a better prognosis than the high-risk group in the total, training, and validation cohorts (all P < .001). This study established a novel nomogram system to predict OS and identify independent prognostic factors in patients with tracheal cancer who underwent surgical intervention. This model has the potential to assist doctors in making decisions regarding treatment options.