This paper investigates the usability of gaze-typing systems for disabled people in a broad perspective that takes into account the usage scenarios and the particular users that these systems benefit. Design goals for a gaze-typing system are identified: productivity above 25 words per minute, robust tracking, high availability, and support of multimodal input. A detailed investigation of the efficiency and user satisfaction with a Danish and a Japanese gaze-typing system compares it to head-and mouse (hand) -typing. We found gaze typing to be more erroneous than the other two modalities. Gaze typing was just as fast as head typing, and both were slower than mouse (hand-) typing. Possibilities for design improvements are discussed.