Tween 20 and 80 are commonly used in biotherapeutics formulations due to their low toxicity and good biocompatibility. However, their quantification still represents an analytical challenge. Based on our expertise in FTIR spectroscopy, we developed a methodology to detect and quantify Tween in biopharmaceutical products. The first figure shows a series of spectra of a therapeutic protein containing different levels of Tween 20. The spectral variations related to the increasing Tween concentrations can be clearly noticed on this figure. Furthermore, using multivariate statistics, we built a predictive model that allows to quantify this detergent even at concentrations lower than 0.1%. The second figure shows the validation of this model, i.e., the application of this model on independent samples: it reports the predicted Tween concentration as a function of the true concentration. The error bars indicate the standard deviation associated with this concentration. With a correlation coefficient of 0.99, the predicted values are highly correlated with the true values, underlining the performance of this model.