Using national survey data on 1422 traders in 18 Chinese wholesale markets, we employ a probit model with sample selection to estimate the determinants of agricultural traders’ credit constraints. The econometric analysis shows that application costs that are highly related to social networks and imperfect screening of applicants by financial institutions both discourage potential borrowers and may make them become “self-rationing.” Credit-constrained traders account for 38.78% of traders seeking loans. The empirical results demonstrate that the probability of being credit-constrained is significantly lower for corporations, traders who have higher value assets, traders with more social networks, and traders in a better micro-finance environment.