Objective This study aimed to explore the association between base excess (BE) and risk of 30-day mortality among patients with acute kidney injury (AKI) in ICU.Methods This retrospective study including ICU patients with AKI from Medical Information Mart for Intensive Care (MIMIC)-IV database. We used multivariate Cox proportional-hazards model to calculate the hazard ratio (HR) for risk of 30-day mortality among patients with AKI. Furthermore, we utilized Cox proportional-hazard model with restrict cubic splines (RCS) to explore the potential no-linear association. Results Of all the 14238 ICU patients with AKI, BE showed U-shaped relationship with risk of 30-day mortality for patients with AKI, and higher or lower BE value could increase the risk. Compared with normal base excess (-3~3 mmol/L), patients with difference groups (BE ≤ -9mmol/L, -9 mmol/L <BE≤-3 mmol/L, 3 mmol/L <BE≤9 mmol/L and BE>9 mmol/L) had different HR for mortality: 1.57(1.40,1.76), 1.26(1.14,1.39), 0.97(0.83,1.12), 1.53(1.17,2.02) respectively. And the RCS analyses also showed U-shaped curve between BE and 30-day mortality risk.Conclusion Our results suggest both higher and lower BE in patients with AKI would increase the risk of 30-day mortality. BE measured at administration could be a critical prognostic indicator for ICU patients with AIK and provide guidance for clinicians.