Abstract Combined hepatocellular-cholangiocarcinoma (cHCC-CCA) is an exceptionally rare form of primary liver malignancy and currently lacks prognostic prediction models. This study aims to develop a nomogram designed to predict cancer-specific survival (CSS) in patients diagnosed with cHCC-CCA. A total of 420 patients diagnosed with cHCC-CCA between 2004 and 2019 were selected from the Surveillance, Epidemiology, and End Results (SEER) database. Patients were randomly assigned to training and validation cohorts in a 7:3 ratio. Cox proportional hazards regression analysis was employed to identify prognostic factors for the construction of the nomogram. The performance and clinical utility of the nomogram were evaluated using the concordance index (C-index), area under the curve (AUC) values, calibration curves, decision curve analysis (DCA), net reclassification improvement (NRI), and integrated discrimination improvement (IDI). Ultimately, Multivariate Cox regression analysis identified 6 variables for the establishment of a nomogram for cHCC-CCA. The C-index, AUC value and calibration curve of the nomogram show that the model has satisfactory accuracy. Additionally, DCA, NRI values (training set: 0.392 for 1-year, 0.425 for 3-year and 0.414 for 5-year CSS prediction), and IDI (training set: 0.165 for 1-year, 0.151 for 3-year and 0.151 for 5-year CSS prediction) indicate that the performance of the established nomogram is significantly better than that based solely on the AJCC standard tumor staging (P