Market and non-market effects of air pollution on human health are estimated for the U.S. for the period from 1970 to 2000. The pollutants include tropospheric ozone, nitrogen dioxide, sulfur dioxide, carbon monoxide, and particulate matter. We develop a methodology for integrating the health effects from exposure to air pollution into the MIT Emissions Prediction and Policy Analysis (EPPA) model, a computable general equilibrium model of the economy that has been widely used to study climate change policy. Benefits of air pollution regulations in USA rose steadily from 1975 to 2000 from $50 billion to $400 billion (from 2.1% to 7.6% of market consumption). Our estimated benefits of regulation are somewhat lower than the original estimates made by the US Environmental Protection Agency, and we trace that result to our development of a stock model of pollutant exposure that predicts that the benefits from reduced chronic air pollution exposure will only be gradually realized. We also estimate the economic burden of uncontrolled levels of air pollution over that period. The estimate of economic benefits and damages depends on the validity of the underlying epidemiological relationships and direct estimates of the consequences of health effects such as lost work and non-work time and increased medical expenses.