This meta-analysis was conducted to assess the association between coffee consumption and prostate cancer risk. Thirteen cohort studies with 34,105 cases and 539,577 participants were included in the meta-analysis. The summary relative risks (RRs) with 95% confidence intervals (CIs) for different coffee intake levels were calculated. Dose-response relationship was assessed using generalized least square trend estimation. The pooled RR for the highest vs. lowest coffee intake was 0.90 (95% CI: 0.85-0.95), with no significant heterogeneity across studies (P = 0.267; I(2) = 17.5%). The dose-response analysis showed a lower cancer risk decreased by 2.5% (RR = 0.975; 95% CI: 0.957-0.995) for every 2 cups/day increment in coffee consumption. Stratifying by geographic region, there was a statistically significant protective influence of coffee on prostate cancer risk among European populations. In subgroup analysis of prostate cancer grade, the summary RRs were 0.89 (95% CI: 0.83-0.96) for nonadvanced, 0.82 (95% CI: 0.61-1.10) for advanced and 0.76 (95% CI: 0.55-1.06) for fatal diseases. Our findings suggest that coffee consumption may be associated with a reduced risk of prostate cancer and it also has an inverse association with nonadvanced prostate cancer. Because of the limited number of studies, more prospective studies with large sample size are needed to confirm this association.