The objective of this study was to assess whether dietary intake of long-chain omega-3 polyunsaturated fatty acids (PUFAs) is associated with lower prevalence of headache in the U.S. This cross-sectional study used data for a nationally representative sample of 12,317 men and women aged ≥ 20 years participating in the National Health and Nutrition Examination Surveys of 1999-2004. Interviewers recorded self-report of severe headache or migraine in the past three months. Eicosapentaenoic acid (EPA) and docosahexaenoic acid (DHA) were quantified from 24-hour dietary recall using the U.S. Department of Agriculture National Nutrient Database. Serum concentration of C-reactive protein, a marker of inflammation and potential mediator of PUFA's analgesic properties, was quantified by latex-enhanced nephelometry. Multivariable generalized linear models estimated prevalence ratios (PR) with 95% confidence limits (CL) for severe headache or migraine adjusting for NHANES cycle, sociodemographic characteristics, body mass index and total energy intake. The unadjusted prevalence of severe headache or migraine was 22.0% (females 28.2%, males 15.5%). In multivariable analysis, greater intake of omega-3 PUFAs was associated with lower prevalence of severe headache or migraine: PR 0.94 (95% CL: 0.88, 0.99, p = 0.035) per log unit increase in EPA, and PR 0.94 (95% CL: 0.90, 0.99, p = 0.023) per log unit increase in DHA. The strength of association was greater for non-Mexican Hispanics than for other racial/ethnic groups but was not attenuated after adjustment for C-reactive protein. In conclusion, higher dietary intakes of EPA and DHA were associated with lower prevalence of headache supporting the hypothesis that omega-3 PUFAs may prevent or reduce headache.