OpenAI is rolling out GPT-6 and an interface that can place interactive visuals, charts, forms, and small tools directly in ChatGPT conversations.
OpenAI is introducing interactive visual responses in ChatGPT alongside the rollout of GPT-6, the company announced on October 7, 2026. Instead of relying only on prose, the chatbot can now present diagrams, charts, forms, and tappable controls within a conversation.
Examples described by OpenAI include a labeled diagram of a seven-speed bicycle, with buttons that highlight components, and a visual guide to Mahjong tiles organized into scrollable groups. ChatGPT can also create task-specific interactive tools, including a retirement savings calculator, a bill-splitting tool, or a simple retro game. These elements appear alongside the model’s written response.
OpenAI says GPT-6 was trained to decide when an interactive visual is more useful than text and how to format it. The feature is arriving with the Sol and Luna versions of GPT-6 in ChatGPT. OpenAI has also said the model improves web searches and can provide partial answers more quickly while continuing to gather information. The company says it is more resistant to attempts to bypass its safety training.
The rollout began globally on October 7 for ChatGPT Plus, Pro, Business, and Enterprise subscribers. Those plans receive the mid-range GPT-6 Sol model. OpenAI said access would expand to Go and free users on Thursday, October 8, with those tiers using the more efficient GPT-6 Luna model.
The change shifts some ChatGPT responses from static explanations toward interactive, in-chat experiences. Users may be able to inspect a visual, change an input, or use a small tool without leaving the conversation. The examples indicate potential uses for explanations and lightweight calculations, though the announcement does not establish that every question will produce an interactive response. Availability varies by subscription tier during the rollout.