The nitrogen (N) nutrition index (NNI) is a reliable indicator of in-season N status in maize (Zea mays L.). Calculation involves repeated field and laboratory laborious and costly measurements. We hypothesize that satellite remote sensing tools that provide information about the spatial-temporal variation of the NNI at the within-field scale, allow us to check for in-season N status. The main objective of this study was to assess predictive models for maize NNI built from multispectral bands, vegetation indices, C-band Synthetic Aperture Radar data (C-SAR), and/or available N in soil (Nav) during V6, V10, V14, and R1 growing stages. Eleven field experiments in maize were conducted in the Argentinean Pampas, applying five N rates (0, 60, 120, 180, and 240 kg N ha-1) at sowing. At V6, V10, V14, and R1, Sentinel-1 and Sentinel-2 satellite observations were obtained, and plants were sampled to determine the NNI. Linear regression models relating NNI to satellite data alone or combined with Nav were calibrated and validated. The NNI ranged from 0.43 to 1.54. The effect of nitrogen rate on NNI and vegetation indices was significant (p < 0.05) although not on C-SAR data. The NNI was predicted with a root mean square error (RMSE) ranging from 0.068 to 0.152 Prediction errors were lower in models that integrated satellite data with Nav (6.4 to 17%). Thus, this study contributed with empirical models based on satellite remote sensing to characterize the in-season maize N status on the within-field scale.