The feasibility of quantifying the perceived active ingredient (P57) in Hoodia gordonii raw material using Fourier transform near- and mid-infrared spectroscopy combined with chemometric techniques was investigated. The concentration of P57 (a triterpene glycoside) was determined in 146 plant samples with liquid chromatography coupled to mass spectrometry and these values were used to develop a calibration model based on the partial least squares projections to latent structures (PLS) and orthogonal projections to latent structures (O-PLS) regression algorithms. The performance of each calibration model was evaluated according to the root mean square error of prediction (RMSEP) and correlation coefficient (R2). The PLS model with 2nd derivative pre-processing predicted P57 content based on the FT-NIR spectra with the best accuracy and a correlation coefficient (R2) value of 0.9629 and the lowest RMSEP of 0.03%. These results demonstrated that FT-NIR spectroscopy can be used to rapidly quantify P57 in H. gordonii raw material with high accuracy.