Service Level Agreement (SLA) has recently garnered increasing attention in cloud computing due to its capability in the definition and the monitoring of the Quality of Service (QoS). SLA is generally generated following a process of negotiation in which the client chooses a subset of clauses among choices predefined by the provider on a “take it or leave it” basis. However, the heterogeneity between client requests and provider offers may result in inappropriate SLA. In addition, the cloud service context may change over the time, which causes a client requirement adjustment, and therefore, the SLA becomes unsatisfactory. In this paper, we propose a cloud SLA negotiation and re‐negotiation approach. Our aim is to ameliorate the SLA negotiation phase by adding the ability to integrate a semantic mapping between client requests and provider offers to generate a suitable SLA document. Moreover, our approach includes a context‐aware system to adapt the SLA throughout reasoning techniques and automatically ensure the re‐negotiation. We develop a prototype, and we test its performance. The results of a case study also show the efficiency of our approach.