This paper proposes a prioritized call admission control (CAC) model to support soft handoff calls with quality of service (QoS) assurances for both the uplink and downlink connections in a CDMA system. CAC is formulated as a combinatorial optimization problem in which the problem objective is to minimize the handoff forced termination rate. The model, which is based on the adaptive channel reservation (ACR) scheme for prioritized calls, adapts to changes in handoff traffic where the associated parameters (reserved channels, and new and handoff call arrival rates) can be varied. To solve the optimization model, iteration-based Lagrangean relaxation is applied by allocating a time budget. We express our achievements in terms of the problem formulation and performance improvement. Computational experiments demonstrate that the proposed ACR scheme outperforms other approaches when there are fewer rather than more channels, and it reduces the handoff call blocking rate more efficiently when the handoff traffic is heavily loaded. Moreover, the model can be adapted to any kind of reservation service.