Despite an emphasis on the prognostic impact of serum soluble interleukin-2 receptor (sIL-2R) at diagnosis in patients with diffuse large B-cell lymphoma (DLBCL), whether the prognostic impact of elevated sIL-2R is linear remains unclear. To verify the presence of a non-linear association between sIL-2R level at diagnosis and overall survival (OS) in patients with newly diagnosed DLBCL, we conducted a multi-center, observational retrospective study. Among 488 analyzable patients, Cox proportional hazards modeling identified serum sIL-2R level at diagnosis as an independent predictor of OS. Multivariate Cox hazard modeling with restricted cubic spline model demonstrated that the relationship between serum sIL-2R level and OS was clearly non-linear (P for effect of sIL-2R = 0.002; P for non-linearity = 0.015). Mortality risk increased gradually as sIL-2R levels increased and plateaued at approximately 5,000 U/mL. Segmented regression analysis revealed that the trend in negative prognostic impact from a gradual increase in serum sIL-2R level changed significantly, with a breakpoint at approximately 2,000 U/mL. Multivariate receiver operating characteristic curves showed a significant improvement in prediction ability when serum sIL-2R level was added to the International Prognostic Index (IPI). Serum sIL-2R level at diagnosis was not only a prognostic factor, but also improved predictive accuracy for OS when incorporated with the IPI. However, the negative correlation between increasing sIL-2R and prognosis was non-linear.