No epidemiologic studies have been conducted to assess the association of intake of dietary vitamin K with the risk of pancreatic cancer. We used prospective data from the Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial between 1993 and 2009 to fill this gap. A total of 101,695 subjects were identified. Dietary intakes of phylloquinone (vitamin K1), menaquinones (vitamin K2), and dihydrophylloquinone (dihydrovitamin K1) were assessed using a food frequency questionnaire. Cox regression was applied to calculate hazard ratios and 95% confidence intervals. During a mean follow-up of 8.86 years (900,744.57 person-years), 361 cases of pancreatic cancer were documented. In the fully adjusted model, dietary intakes of phylloquinone (for quartile 4 vs. quartile 1, hazard ratio (HR) = 0.57, 95% confidence interval (CI): 0.39, 0.83; P for trend = 0.002) and dihydrophylloquinone (for quartile 4 vs. quartile 1, HR = 0.59; 95% CI: 0.41, 0.85; P for trend = 0.006), but not menaquinones (for quartile 4 vs. quartile 1, HR = 0.93; 95% CI: 0.65, 1.33; P for trend = 0.816), were found to be inversely associated with the risk of pancreatic cancer in a nonlinear dose-response manner (all P values for nonlinearity < 0.05), and this was not modified by predefined stratification factors and remained in sensitivity analyses. In conclusion, dietary intakes of phylloquinone and dihydrophylloquinone, but not menaquinones, confer a lower risk of pancreatic cancer. Future studies should confirm our findings.