Low-cost sensors could increase the spatial granularity of air-quality monitoring at 700–1000 times less cost than reference stations (2026 prices), but few field studies evaluate them for gases. This study evaluates a three-tier architecture (low-cost metal oxide and optical, mid-cost electrochemical, high-cost government reference) over 10 months at two London sites, 1.6 km apart. The low-cost sensors and mid-cost ${\mathrm{NO}}_2$ sensor were calibrated with manufacturer curves, linear regression on temperature and relative humidity, and machine learning (ML). After field calibration, the low-cost ${\mathrm{PM}}_{2.5}$ sensor explains over half the reference variance at both sites, and linear calibration equals ML. The low-cost ${\mathrm{NO}}_2$ sensor agrees less with its reference than the ${\mathrm{PM}}_{2.5}$ sensor. The low-cost sensors explain over half the variance of a factory-calibrated mid-cost electrochemical CO sensor at both sites only with ML. The mid-cost ${\mathrm{NO}}_2$ and low-cost O₃ sensors fail under all three methods. Calibrations trained on April–October 2025 stop describing November 2025–February 2026 data for ${\mathrm{NO}}_2$ at both sites and CO at one, whereas ${\mathrm{PM}}_{2.5}$ stays stable. Transferred between sites, ${\mathrm{PM}}_{2.5}$ calibrations reach $R^2\ge 0.56$ and gas calibrations $R^2\le 0.28$. Low-cost ${\mathrm{PM}}_{2.5}$ sensors calibrated at a reference site could serve neighborhood-scale monitoring where reference stations are absent, whereas ${\mathrm{NO}}_2$ needs co-location.