Suicide rates have been related to educational level and other socioeconomic statuses. However, no prospective study has examined the association between educational level and the risk of suicide in Japan.We examined the association of education level and suicide risk in a population-based cohort of Japanese men and women aged 40-59 years in the Japan Public Health Center-based Prospective Study Cohort I. In the baseline survey initiated in 1990, a total of 46 156 subjects (21 829 men and 24 327 women) completed a self-administered questionnaire, which included a query of educational level, and were followed up until the end of December 2011. Educational levels were categorized into four groups (junior high school, high school, junior or career college, and university or higher education). During a median follow-up of 21.6 years, the hazard ratios (HRs) and 95% confidence intervals (CIs) of suicide according to educational level were estimated using the Cox proportional hazards regression model adjusted for age; study area; previous history of stroke, ischemic heart disease, or cancer; self-reported stress; alcohol consumption; smoking; living with spouse; and employment status. A total of 299 deaths attributed to suicide occurred.The HR for university graduates or those with higher education versus junior high school graduates was 0.47 (95% CI, 0.24-0.94) in men, and that for high school graduates versus junior high school graduates was 0.44 (95% CI, 0.24-0.79) in women.High educational levels were associated with a reduced risk of suicide for both Japanese men and women.