A service level agreement (SLA) system is provided for multi-tenant cloud computing to enable provisioning of computing instances for tenants with a networking SLA. A networking SLA may specify a bandwidth requirement, for example, between instances to be scheduled for a tenant in a datacenter. The SLA system evaluates nodes in the datacenter based on a remaining capacity of links associated with nodes implementing the networking SLA. A modular system is provided to enable integration of the SLA system into existing cloud computing infrastructures. The cloud management system may query the SLA system to determine nodes in the datacenter capable of meeting a networking SLA. The list may be ordered to indicate nodes having better capacity to fulfill the networking SLA. The cloud management system can utilize the ordered list of nodes in scheduling instance deployments for tenant requests.