Background. The present study aimed to investigate the prognostic value of serum ferritin in critically ill patients with sepsis by using the MIMIC-IV database. Methods. Data were extracted from the MIMIC-IV database. Adult patients who met the sepsis-3 criteria and had the test of ferritin were included. Patients were divided into subgroups according to the initial serum ferritin. The association between initial serum ferritin and in-hospital mortality was performed by using Lowessregression, logistic regression, and ROC analysis. Subgroup analysis was used to search for the interacting factors and verify the robustness of the results. Results. Analysis of the 2,451 patients revealed a positive linear relationship between serum ferritin and in-hospital mortality. Patients with high-ferritin had a higher risk of in-hospital mortality, but no significant association was found in the low-ferritin subgroup compared with those whose ferritin was in the normal reference range. Serum ferritin had moderate predictive power for in-hospital mortality (AUC = 0.651), with an optimal cut-off value of 591.5 ng/ml. Ferritin ≥591.5 ng/ml acted as an independent prognostic predictor of in-hospital mortality, which increased the risk of in-hospital mortality by 119%. Our findings were still robust in subgroup analysis, and acute kidney injury and anemia were considered interactive factors. Conclusion. High-level serum ferritin was an independent prognostic marker for the prediction of mortality in patients with sepsis. Further high-quality research is needed to confirm the relationship between ferritin and the prognosis of septic patients.