GPT-4 Vision

GPT-4 Vision (GPT-4V) is the multimodal extension of the OpenAI model, enabling advanced visual analysis and complex data interpretation from image and text inputs.

GPT-4 Vision (GPT-4V), a core capability of the OpenAI GPT-4 model, is a powerful multimodal system. It seamlessly processes interleaved image and text inputs, allowing users to perform complex visual tasks: analyzing data in charts and graphs, transcribing handwritten text, and even generating website code from a visual design. This technology excels at object detection, spatial relationship understanding, and providing nuanced interpretations of complex scenes, significantly expanding AI's application scope beyond text-only models.

https://platform.openai.com/docs/guides/vision