This paper estimates the shadow wages of unpaid family farm laborers in Korean agriculture, using a farm-level cross-sectional data set. Such measurements are obtained from the dual relationship between the cost function and the input distance function. Emphasis is on estimating a stochastic multi-output input distance function, which accommodates multiple outputs and inputs into the frontier framework. The empirical evidence suggests that the average wage of hired farm laborers is significantly higher than the average shadow wage of family farm laborers. This, however, may be the result of the heavy reliance on hired labor during the peak seasons. Notably, the average shadow wage of female laborers is lower than the average for hired female workers determined by rural labor market, but the median values for the two groups are the same. The results of quantile regressions are also indicative of shadow wage variations according to gender, farm size, farm characteristics, zone, and region.