xAI, a GenAI chatbot startup founded by Elon Musk, has introduced Grok-1.5V, a multimodal model capable of interpreting textual and visual data.

Grok-1.5V claims to have better text processing abilities and the ability to comprehend varied types of visual data, including drawings, photographs, charts, and diagrams. It is a first from X.ai, merging text and visual comprehension in a single model.

According to the company, Grok-1.5V is competitive with current multimodal models in various domains, such as multidisciplinary reasoning and understanding of documents, science diagrams, charts, and images.

Analyst Quicktake: xAI previously introduced Grok 1.5 , which has improved reasoning capabilities and open-sourced the foundational code of its Grok AI model. It also expanded Grok chatbot access to the social network X’s premium tier subscribers, expanding the availability of the chatbot last week.