Several studies, notably from rural areas, have shown an association between mobility and HIV infection. However, reasons for this association are poorly documented. In this study, we examined the relationship between mobility, sexual behavior, and HIV infection in an urban population of Cameroon. A representative sample of 896 men and 1017 women were interviewed and tested for HIV infection and other sexually transmitted infections in Yaoundé in 1997. Mobile and nonmobile people were compared with respect to sociodemographic attributes, risk exposure, condom use, and prevalence of HIV infection, using descriptive statistics and multivariate logistic regression. Seventy-three percent of men and 68% of women reported at least 1 trip outside of Yaoundé in the preceding 12 months. Among men, the prevalence of HIV infection increased with time away from town. Men who declared no absence were 5 times less likely to be infected than were those away for >31 days (1.4% vs. 7.6%, respectively; adjusted odds ratio, 0.23; 95% confidence interval, 0.07-0.82). Furthermore, mobile men reported more risky sexual behaviors (ie, more partners and more one-off contacts). For women, the pattern was less clear: differences in the prevalence of HIV infection were less marked for nonmobile than for mobile women (6.9% vs. 9.8%, respectively; P > 0.1). This study suggests that characteristics of male mobility may be an important feature of the HIV epidemic in Cameroon.