This paper introduces a method realizing dynamic provisioning of services in a distributed environment. Depending on a particular state of infrastructure the call of a service can lead to a new instance in the infrastructure or to using an existing instance. Hence, the dynamic deployment allows optimized distribution of service instances within a certain infrastructure. The paper introduces a context model for services that are registered in a distributed runtime environment. Furthermore, algorithms are introduced determining the need for instantiation as well as the best location for deployment. Hence, the best location is determined by correlating the context model, the certain state of infrastructure as well as data transfer costs.