Urban air quality simulation is an important tool to understand the impacts of air pollution. However, the simulations are often computationally expensive, and require extensive data on pollutant sources. This data can be obtained through sparse measurements, or through traffic simulation. Modeling chains combine the simulations of multiple models to provide the most accurate representation possible, however the need to solve multiple models for each simulation increases computational costs even more. In this paper we construct a meta-modeling chain for urban atmospheric pollution, from dynamic traffic modeling to pollutant dispersion-reaction. Reduced basis methods (RBM) aim to compute a cheap and accurate approximation of a physical state using approximation spaces made of a suitable sample of solutions to the model. One of the keys of these techniques is the decomposition of the computational work into an expensive one-time offline stage and a low-cost parameter-dependent on line stage. Traditional RBMs require modifying the assembly routines of the computational code, an intrusive procedure which may be impossible in cases of operational model codes. We propose a non-intrusive reduced order scheme, and study its application to a full chain of operational models. Reduced basis are constructed using principal component analysis (PCA), and the concentrations fields are approximated as projections onto this reduced space. We use statistical emulation to approximate projection coefficients in a non-intrusive manner. We apply a multi-level meta-modeling technique to a chain using the dynamic traffic assignment model LADTA, the emissions database COPERT IV, and the Gaussian dispersion-reaction air quality model SIRANE to a case study on the city of Clermont-Ferrand with over 45000 daily traffic observations, a 47000-link road network, a simulation domain covering 180km^2 , and assess the results using hourly NO2 concentration observations measured at stations in the agglomeration. We reduce computational times from nearly 3 hours per simulation to under 0.1 second, while maintaining accuracy comparable to the original models. The low cost of the meta-model chain and its non-intrusive character demonstrate the versatility of the method, and the utility for long-term or many-query air quality study.