Osteoarthritis (OA) causes chronic pain, physical disability, and mental health deterioration and reduces the quality of life of patients. Sleep is an important factor in the recovery, and adequate sleep is important for quality of life. Several features of patients with OA can affect sleep time, and sleep also affects OA. We investigated the relationship between OA and sleep duration. Data for 2010-2012 were collected from the Korea National Health and Nutrition Examination Survey. We included 11,540 participants (4915 men and 6625 women). Patients with OA were defined as participants with knee/hip joint pain and radiographic changes of the knee/hip joints. Sleep time was divided into 4 sections as follows: (1) 0-3h, (2) 4-5h, (3) 6-7h, and (4) ≥ 8h. Sleep time of 6 and 7h was the most frequent and set as the reference time. In the multiple logistic regression model, the patients who slept for 0-3 and 4-5h had odds ratios (ORs) of 2.28 (95% confidence interval [CI] 1.14-4.55) and 1.38 (95% CI 1.01-1.89) for men and 1.63 (95% CI 1.19-2.24) and 1.26 (95% CI 1.08-1.47) for women, respectively, for having OA. The prevalence of OA was lowest in the participants who had 6-7h of sleep and progressively increased with shorter sleep time. Thus, sleep duration was significantly associated with OA.