In this paper, the performance of a steady-state visually evoked potential (SSVEP)-based brain-computer interface (BCI) was evaluated after reducing the number of electroencephalography (EEG) electrodes used for recording. Our aim was the comparison of the performance using a different number of electrodes, as well as determining the best electrode locations. The main benefit of determining the most efficient electrode sites can be the shortening of the preparation time needed for the setup of the BCI system. The performance of the BCI was measured with a different number of EEG electrodes reduced from initially sixteen to six electrodes as the intermediate step, and finally to four electrodes. Seventeen subjects participated in this study, seven were male and ten female. The mean ITRs were 27.50 bit/min, 24.09 bit/min, and 23.23 bit/min for sixteen, six and four EEG electrodes, respectively. However, not all users managed to use the system with less electrodes, as one user did not manage to control the system with six electrodes, and four of the seventeen users were not able to finish the spelling tasks with four electrodes. With a reduced number of electrodes, a high accuracy can be achieved while retaining a fair spelling speed.