OpenAI has been working this year to make ChatGPT more than a text-only service. Now, it’s rolling out a new intelligent user interface to bring interactive graphics, images and other visual displays into your AI answers, powered by GPT-6. The interface will be available to free users this week.

If you ask ChatGPT to explain the offside rule in English football, the chatbot could create interactive graphics that let you adjust each player’s position on the field to see where the boundary lines would be in each scenario. You can also have the AI plan your dinner party menu and grocery list, with a slider you can adjust based on the expected number of guests. ChatGPT creates these custom images and graphics, but they’re based on information pulled from online sources, which should be cited in each answer.

This new UI is powered by OpenAI’s latest flagship model, GPT-6. In addition to the new answer format, all ChatGPT users will have access to GPT-6 this week. It’s rolling out to Plus and Pro users on Wednesday, with plans to bring it to free users later in the week.

More complex tasks for AI models — like deep reasoning, image generation and running AI agents — eat up users’ allotted tokens or usage limits. OpenAI told CNET that while there’s more information in these AI images, it doesn’t expect this new visual interface to “meaningfully” change usage because “by and large it’s very efficient.” We’ll have to wait and see if that proves true for most users.

Despite being the company that made tech history with its text-synthesis AI model, OpenAI has worked to move its chatbot beyond text alone. It has invested in its voice mode, with new AI voice models that are better at conversation and language translation. Its image generation efforts, including ChatGPT Images 2.5, are also bolstering the company’s efforts to create more multimodal experiences for customers. The idea is to give users more options to customize how they use ChatGPT. But for now, this new intelligent user interface is limited to text prompts, though you can use voice-to-text to dictate your requests, OpenAI says.

Katelyn Chedraoui

Reporter 2

Katelyn is a reporter with CNET covering artificial intelligence, including chatbots, image and video generators. Her work explores how new AI technology is infiltrating our lives, shaping the content we consume on social media and affecting the people behind the screens. She graduated from the University of North Carolina at Chapel Hill with a degree in media and journalism. You can reach her at kchedraoui@cnet.com.

See full bio