Apertus 1.5 supports native image and audio input
On October 15, 2026, Swiss AI released Apertus 1.5, adding native image and audio understanding capabilities on top of 1.0. The model converts images and audio into discrete tokens via early fusion and feeds them into the same sequence as text, with the architecture unchanged; it only understands multimodal input and outputs text only. The official announcement also states that Apertus 1.5 adds a thinking mode and a 262,144-token context window, four times larger than 1.0. According to the official statement, the 8B version outperforms open-source models of the same scale on instruction-following and multilingual tasks, its multimodal performance is close to Gemma 4 12B, and the training data mixture, preference data, and intermediate checkpoints for each stage are also released. There are currently no subsequent developments.
On October 15, 2026, Swiss AI released Apertus 1.5, adding native image and audio understanding capabilities on top of 1.0. The model converts images and audio into discrete tokens via early fusion and feeds them into the same sequence as text, with the architecture unchanged; it only understands multimodal input and outputs text only. The official announcement also states that Apertus 1.5 adds a thinking mode and a 262,144-token context window, four times larger than 1.0. According to the offic
Matched fieldsSummary