Introduction: The aim of this study was to investigate the relationship between the AST/ALT ratio and osteopenia or osteoporosis in patients with type 2 diabetes mellitus (T2DM). Methods: A total of 589 patients with T2DM were divided into two groups based on T-score: T-score ≥ −1.0 group, normal bone mineral density and T-score < −1.0 group, osteopenia or osteoporosis (OP). The association between the AST/ALT ratio and osteopenia/OP was evaluated by multivariate analyses. The receiver operating characteristic (ROC) curves were used to estimate the diagnostic performance according to the area under the ROC curve (AUC). Results: The patients in the T-score < −1.0 group showed significantly higher AST/ALT level than those in the T-score ≥ −1.0 group (0.93 ± 0.16 vs 1.17 ± 0.24, P < 0.001). According to the interquartile range of the AST/ALT ratio, the participants were divided into four groups: Q1 (0.650, 0.874), Q2 (0.875, 0.999), Q3 (1.000, 1.173) and Q4 (1.174, 1.917). After adjustment for confounding factors, compared with Q1 of the AST/ALT level, subjects in Q3 and Q4 remained more likely to have osteopenia or osteoporosis (Q3, OR 3.478, 95% CI 1.641–7.411; Q4, OR 15.278, 95% CI 6.377–36.837). The AST/ALT ratio provided an AUC value of 0.81 (95% CI 0.77–0.84) for osteopenia or osteoporosis in patients with T2DM. Conclusion: An elevated AST/ALT ratio is associated with the evaluated risk of osteopenia/OP in patients with T2DM. The AST/ALT ratio, a practical and cost-effective biomarker, may be a potential predictor of osteopenia/OP in patients with T2DM.