Glucose and lactate profiles in Chinese hamster ovary cell cultures were accurately monitored in real time and in situ during three bioreactor batch cultures lasting 11,15, and 15 days performed within a 60-day period. Monitoring was accomplished using in situ-collected mid-infrared spectra analyzed with a priori one-time established partial least-squares regression models. The robustness of the technique was demonstrated by application of these models without modification after 2.3 years. Neither recalibration nor instrument maintenance was required during the 2.3-year period, except for the daily filling of liquid nitrogen for detector cooling during operation. The lactate calibration model yielded accurate absolute concentration estimations during each of the batch cultures with standard errors of estimate from 1 to 3 mM. The a priori-established glucose calibration model yielded concentration estimations with an off-set, which was constant throughout a culture. Adjustment of the off-set before inoculation resulted in accurate concentration estimations with Standard errors of estimate of approximately 1 m M for each of the bioreactor cultures. Sensitivity in detecting differences of 0.5 mM and selectivity against variation of one metabolite while the other was kept constant was demonstrated during standard additions of either glucose or lactate. The sensor system proved to be reliable, simple, accurate, sterile, and capable of long-term automatic operation and is considered to be mature enough to be routinely applied for in situ (on-line) cell culture monitoring.