This paper develops a single-vendor single-retailer supply chain for multi-product. The proposed model is based on Vendor Managed Inventory (VMI) approach and vendor uses the retailer's data for better decision making. The number of orders and available capital are the constraints of the model. In this system, shortages are backordered; therefore, the vendor’s warehouse capacity is another limitation of the problem. After the model formulation, an Integer Nonlinear Programming problem will be provided; hence, a metaheuristic algorithm called Imperialist Competitive Algorithm has been used to solve the model. Consequently, order quantities, number of shipments received by a retailer and maximum backorder levels for products have been determined with regard to cost consideration. Then, a numerical example is presented to describe the sufficiency of the proposed strategy. Furthermore, the model is also solved using Particle Swarm Optimization (PSO) and compared with the Imperialist Competitive Algorithm (ICA).