We consider stochastic differential equations (SDEs) driven by Feller processes which are themselves solutions of multivariate Lévy driven SDEs. The solutions of these ‘iterated SDEs’ are shown to be non-Markovian. However, the process consisting of the driving process and the solution is Markov and even Feller in the case of bounded coefficients. The generator as well as the semimartingale characteristics of this process are calculated explicitly and fine properties of the solution are derived via the probabilistic symbol. A short simulation study and an outlook in the direction of stochastic modeling round out the paper.