Incomplete cuts during laser fusion cutting result in a closed kerf, preventing the workpiece from detaching from the metal sheet, in turn necessitating rework or rejection. We demonstrate the approach of a vision transformer, used for image classification, to detect cut interruption during laser fusion cutting of steel and aluminum sheets. With events impending an incomplete cut in steel, we attempt to predict cut interruption before they even occur. To build a data set for training, cutting experiments are carried out with a 4 kW fiber laser, forcing incomplete cuts by varying the process parameters laser power and feed rate. The thermal radiation from the process zone during the cutting process is captured by a camera with a size of 256 px ×256 px at sample rates of 20∙10³ frames per seconds. The kerf is recorded with a spectral sensitivity between 400 and 700 nm, without external illumination, allowing the melt to be observed in the range of the visual spectrum. The vision transformer model, which is used for image classification, splits the image into patches, linear embedded with an added position embedding and feed to a standard transformer encoder. For training the model, a set of images is labeled for the respective classes of a complete and incomplete cut for steel and aluminum and impending incomplete cut for steel. With the trained model, incomplete cuts in steel and aluminum can then be recognized and impending incomplete cuts in steel can be predicted in advance.