A core public policy question for jail diversion programs, regardless of what outcomes they achieve, is whether and to what extent they generate cost savings. Apart from a general pattern of cost shifting from the criminal justice system to the community mental health system, studies on the costs of jail diversion programs have yielded limited and equivocal results. In response to the mixed results on cost findings, we tested a simulation model to project the fiscal impact of jail diversion programs using data from actual criminal justice and mental health systems and the best outcome data from the literature. Using data from Travis County, Texas, in 2006 and 2007, our simulations that produced a net savings to the county had two key findings: (a) Unless the most serious misdemeanants and low-level felons are included for diversion, there will be no cost savings since there are too few jails days avoided; and (b) the cost burden was shifted from the criminal justice system to the community-based service system, which is already strained for resources.