This paper discusses how the early phases of developing embedded electronic systems can be improved by enhanced modelling of cost and performance that includes explicithandling of uncertainties. The approach is to add cost information to existing UML models,capture uncertainties using probability distributions, and use Monte Carlo simulation to analyze the risk of not reaching the cost targets. It is demonstrated how the information obtained can be used when evaluating different architecture alternatives, while including both development and product cost as well as risk in the trade-off