To construct predictive models for predicting overall survival (OS) and cancer-specific survival (CSS) of patients with buccal mucosa cancer (BMC). Data of 936 patients with BMC were extracted from the Surveillance, Epidemiology, and End Results (SEER) database from 2004 to 2015. Nomograms were constructed based on multivariate Cox regression analyses, and validated using calibration plots, time-dependent receiver operating characteristic curves, and decision curve analyses. Age at diagnosis, marital status, grade, histopathology, SEER stage, tumor size, and surgery were associated with OS, whereas age at diagnosis, grade, histopathology, SEER stage, tumor size, and surgery were associated with CSS (all P < .05). The concordance indexes for OS and CSS were 0.79 and 0.80 in the training cohort, respectively, and those in the validation cohort were 0.78 and 0.80. Time-dependent receiver operating characteristic curves showed great predictability in nomograms. Decision curve analyses demonstrated good clinical value for OS (4%-88%) and CSS (3%-77%) nomograms. Patients were stratified into 3 risk groups, with the worst prognosis in the high-risk subgroup (P < .001). We developed and validated 2 nomograms predicting OS and CSS and established the corresponding risk classification systems in patients with BMC. These models assisted in precise administration of individual therapeutic regimens.