To explore the clinical characteristics and prognostic factors of patients with primary parotid gland lymphoma, and construct a prognostic model nomogram for patients with primary diffuse large B-cell lymphoma (DLBCL) of parotid gland. Primary parotid gland lymphoma and primary DLBCL of parotid gland patients from 1984 to 2016 were identified from the Surveillance, Epidemiology, and End Results (SEER) database. Univariate and multivariate Cox regression analysis were conducted to determine the independent prognostic factors of primary parotid gland lymphoma and primary DLBCL of parotid gland, respectively. According to the established independent prognostic factors of primary DLBCL of parotid gland, nomogram was built to predict 3- and 5-year survival, and the discrimination and calibration of the model were evaluated by concordance index (C-index) and calibration plots. A total of 2 610 patients with primary parotid gland lymphoma were identified. Their median age was 66(15-99) years old, the male to female ratio was 1∶1.8, and 20.5% of them was primary DLBCL of parotid gland, which was the most common histological subtype in aggressive lymphomas. Multivariate Cox regression analysis showed that sex, age, Ann Arbor stage, years of diagnosis, marital status, histological subtype, surgery, and radiation were the independent prognostic factors of primary parotid gland lymphoma, while age, marital status, surgery, and chemotherapy were the independent prognostic factors of primary DLBCL of parotid gland. The C-index of the prediction model was 0.702(95%CI: 0.696-0.768), reflecting a good discrimination ability. The predicted value probability of the calibration plots was close to the actual value probability, reflecting a good accuracy ability. Sex, age, Ann Arbor stage, years of diagnosis, marital status, histological subtype, surgery, and radiation were the independent prognostic factors of primary parotid gland lymphoma. The nomogram survival prediction model for primary DLBCL of parotid gland patients can assist clinical decision effectively.