This paper introduces Vision, a novel 175-billion parameter multimodal AI model.Vision is trained from scratch to natively understand text, images, video, and audioand to generate text and images, setting it apart from existing models. Developedwith a focus on incorporating Indian context, values, and culture, Vision aims to em-power users with a culturally relevant AI experience. A unique security feature allowsgenerated images to be backtracked to Vision, mitigating concerns about potential mis-use for misinformation. Evaluations on standard benchmarks demonstrate that Visionachieves state-of-the-art performance in a diverse range of tasks, including reasoning,solving mathematical problems, code generation, and image understanding. Further-more, Vision exhibits remarkable proficiency in multilingual chat, supporting a widearray of global languages as well as regional Indian languages such as Hindi, Punjabi,and Marathi. We believe that Vision represents a significant step towards buildingmore inclusive and culturally relevant AI systems, with the potential to positively im-pact various domains in India and beyond.