Purpose To update the evidence of anti-mullerian hormone (AMH) as predictive factors for live birth outcome in women undergoing assisted conception and discover the modulating effect of age. Methods PubMed, Embase, Medline, and Web of Science were searched for studies published until June 2021. We included studies that measured serum AMH levels and reported the subsequent live birth outcomes. Random effects models and hierarchical summary receiver operating characteristics (HSROC) models were used. The QUADAS-2 checklist was employed to assess the quality of the included studies. Results We included 27 studies (27,029 women) investigating the relationship between AMH and live birth outcome after assisted conception. The diagnostic odds ratios (DOR) from random effects models were ruled out due to high heterogeneity. Our findings suggested that AMH was associated with live birth. The DOR was 2.21 (95% CI 1.89-2.59), and 2.49 (95% CI 1.26-4.91) for studies on women with unspecified ovarian reserve and women with low ovarian reserve, respectively. The DOR of those with advanced ages was 2.50 (95% CI 1.87-2.60). For younger women, the DOR was 1.41 (95% CI 0.99-2.02). HSROCs showed that AMH had no predictive ability towards live birth in women with diminished ovarian reserve or younger age. Exclusion of Chinese cohorts lowered the heterogeneity. Conclusions This study revealed that AMH had better prediction for live birth in advanced-age women. AMH may have implicative predictive value for assisted conception counseling of couples of advanced ages.