From the source
Apertus 1.5, our latest model release, extends the 8B and 70B Apertus 1.0 models with image understanding, an optional thinking mode, a four times longer context window, improved instruction-following, and better tool use.
Apertus 1.5 is a continued pretraining of Apertus 1.0: we added 4 trillion tokens of text and multimodal training data to the 8B model and 2 trillion tokens to the 70B model.
As with every Apertus release, the models are fully open: open weights, open data, open values, and full training details.
The updated 8B and 70B models were released on July 24, 2026.
We are working with inference providers to make them available on multiple platforms.
Key Enhancements Native Image Understanding: Apertus 1.5 accepts images alongside text, bringing documents, diagrams, and photos into the conversation.
The models can also process spoken language, though this remains experimental.
Thinking Mode: The models can be switched into a thinking mode to reason about the input before answering, which improves performance on reasoning problems.
Long Context: The context window grows to 262,144 tokens, a four-fold increase over Apertus 1.0.
…
