Cirrhosis is the end stage of many chronic liver diseases, which seriously affects the quality of life of patients. The alkaline phosphatase to albumin ratio (APAR) index is a new indicator related to the prognostic risk of many diseases. This study was aimed at exploring the association between the APAR index and the risk of all-cause mortality in patients with cirrhosis. Patients with cirrhosis who were 18 years of age or older and admitted to the intensive care unit were included from the Medical Information Mart for Intensive Care IV (MIMIC-IV) - Version 3.0 database in this study. The primary endpoint of this study was all-cause mortality at 365- days, with secondary endpoints at 90-days and 28-days after admission. The hazard ratio (HR) and 95% CI between the APAR index and endpoints were calculated using the Cox proportional hazards model. A restricted cubic spline (RCS) regression model was created to explore the relationship between the APAR index and cirrhosis. Furthermore, we explored the predictive value of the APAR index in different populations of cirrhosis through subgroup analysis. A total of 2,109 patients with cirrhosis were included from the MIMIC-IV database. After adjusting for potential covariates, APAR as a continuous variable was significantly positively associated with all-cause mortality at 28-days (HR: 2.007, 95% CI: 1.369, 2.948; P < 0.001), 90-days (HR: 2.392, 95% CI: 1.642, 3.495; P < 0.001), and 365-days (HR: 2.418, 95% CI: 1.660, 3.534; P < 0.001) in cirrhotic patients. When APAR was a categorical variable, compared with patients in the lower APAR group, the risk of 365-days all-cause mortality in patients of the higher APAR group significantly increased (HR: 1.451, 95%CI: 1.197, 1.758). APAR was linearly related to all-cause mortality at 28-days, 90-days and 365-days after admission (P for non-linearity = 0.221, 0.390, and 0.344, respectively). Subgroup analysis indicated that among patients with cirrhosis complicated with hepatorenal syndrome, those without spontaneous peritonitis or portal hypertension/esophageal varices, and those receiving human albumin infusion, elevated APAR levels were significantly associated with an increased risk of long-term death. A higher APAR index is significantly associated with the risk of all-cause mortality in cirrhosis. APAR may be a potential biomarker for evaluating the long-term prognosis of critically ill patients with cirrhosis.