The interaction of advanced glycation end-products (AGEs) with their receptor (RAGE) elicits oxidative stress and inflammation, which is involved in the development of breast cancer. However, large-scale population-based evidence exploring genetically modified circulating levels of AGEs-RAGE axis with risk and mortality of breast cancer is scarce. We recruited 1051 pairs of age-matched breast cancers and controls and measured plasma AGEs and sRAGE concentrations by enzyme-linked immunosorbent assay (ELISA). Multivariate logistic regression and Cox proportional hazard model were used to calculate the effects of plasma levels and genetic variants of the AGEs-RAGE axis and their combined effects on breast cancer risk and prognosis, respectively. Furthermore, linear regression was performed to assess the modifications in plasma AGEs/sRAGE levels by genetic predisposition. Higher levels of AGEs and AGEs/sRAGE-ratio were associated with an increased risk of breast cancer, but sRAGE levels were negatively associated with breast cancer risk, especially in women <60 years. We also observed a positive association between AGEs and the bad prognosis of breast cancer. Although we did not observe a significant contribution of genetic variants to breast cancer risk, rs2070600 and rs1800624 in the AGER gene were dose-dependently correlated with sRAGE levels. Further, compared to the haplotype CT at the lowest quartile of AGEs, haplotypes TT and TA were prominently associated with breast cancer risk in the highest quartile of AGEs. This study depicted a significant association between circulating levels of AGEs-RAGE axis and breast cancer risk and mortality and revealed the potential of plasma AGEs, especially coupled with AGER polymorphism as biomarkers of breast cancer.