Compound availability is a critical property for design prioritization across the drug discovery pipeline. Historically, and despite its multiple limitations, compound-oriented synthetic accessibility scores have been used as proxies for this problem. However, the size of the catalogues of commercially available molecules has dramatically increased over the last decade, redefining the problem of compound accessibility as a matter of budget. In this paper we show that if compound prices are an alternative proxy for compound availability, then synthetic accessibility scores are not effective strategies for assessing availability. Instead, we learn how to predict prices directly from the catalogues. Our approached, CopriNet, is a retrosynthesis-free deep learning model trained on pairs of compound/prices extracted from the Mcule catalogue. CoPriNet is able to provide price predictions that exhibit far better correlation with actual compound prices than any synthetic accessibility measurement. Moreover, unlike standard retrosynthesis methods, CoPriNet is rapid, comparable in execution time to popular synthetic accessibility metrics and thus is suitable for high-throughput experiments including virtual screening and de novo compound generation.