Current cloud application program interface (API) recommendation methods mainly use similarity calculation or historical calls of Mashup to generate recommendation results, while ignoring the beneficial functional complementarity (FC) between Mashup and cloud API.To address the above issue, a FC relationship enhanced cloud API recommendation approach was proposed.Firstly, label co-occurrence was applied to describe the FC relationship.Then, the FC score was calculated to describe the degree of FC between the cloud API and the Mashup, and the FC vector was learned to describe the potential FC relationship.Based on this, FC scores and FC vectors were embedded into the cloud API recommendation model, so that FC relationship played a key role in the cloud API recommendation process.Experiments were conducted on real-world cloud API datasets, and the AUC, F1 and HR@5 of the proposed approach improved by an average of 2.32%, 1.86% and 9.15%, respectively, in the sparse scenario.Finally, the proposed approach can improve the accuracy of cloud API recommendation results, while improving the recommendation performance of long-tail cloud API.