Background. Solitary plasmacytoma of bone (SPB) is an isolated plasmacytoma of bone origin, most commonly seen in the elderly, with a poor prognosis. So far, there is no precise nomogram to predict the overall survival (OS) of elderly patients with SPB. Our goal is to construct and validate a nomogram for elderly patients with SPB. Methods. This study collected all elderly patients with SPB in the Surveillance, Epidemiology and End Results (SEER) database from 2000 to 2018, and the variables included were age, sex, race, marital status, primary site, grade, stage, surgery, chemotherapy, and radiotherapy. Independent prognostic factors were identified using univariate and multivariate Cox analysis. The nomogram was constructed to predict 1-, 2-, and 3-year OS of elderly patients with SPB. The receiver-operating characteristic (ROC) and the calibration curves were used to differentiate and calibrate the nomogram. The clinical validity of the nomogram was evaluated by decision curve analysis (DCA). The total OS scores of all elderly SPB patients were calculated and divided into two risk subgroups for comparison. Results. A total of 1837 patients diagnosed with SPB were screened from the SEER database, with a final inclusion of 1180 patients ( age ≥ 60 years). Age, radiotherapy, and marital status were significantly correlated with OS. These characteristics were further incorporated into the creation of the nomogram for predicting 1-, 2-, and 3-year OS of elderly patients with SPB. For this predictive model, the area under the ROC curves, calibration curves, and DCA have good performance in terms of differentiation, consistency, and validity, respectively. In addition, patients in the high-risk group (≥96) had a worse prognosis than those in the low-risk group (<96). Conclusion. We constructed a nomogram and a risk classification system that could provide an intuitive and effective tool for clinicians to better predict the OS of elderly SPB patients.