What Is ChatGPT's Intelligent UI, and Can You Turn It Off? (October 2026)
On October 7, 2026, OpenAI moved regular ChatGPT chat to GPT-6 and added Intelligent UI: answers that arrive as charts, buttons, forms, and small calculators instead of plain text. Here's what changed, which plans get it and when, whether you can dial it back, and what it means if you use ChatGPT for work.
See Claude set up for your job
Skip the theory — pick your profession and get the real workflows, ready-to-use prompts, and exact setup for your work.
TL;DR: On October 7, 2026, OpenAI switched the regular ChatGPT Chat tab to GPT-6 and launched Intelligent UI: answers can now arrive as interactive charts, diagrams, buttons, forms, and small calculators instead of mostly text. Plus, Pro, Business, and Enterprise get it first, on GPT-6 Sol; Free and Go follow on October 8, on GPT-6 Luna. ChatGPT Work and Codex are unchanged. You can't fully switch the visuals off, but OpenAI says you'll be able to dial them back. If you use ChatGPT for work, the main thing to change is habit: check the numbers behind any chart before you reuse it.
For most of its life, ChatGPT has answered in text, with the occasional table or image. This update changes the default. Ask how a bicycle works and you may get a labeled diagram you can click into; ask about savings and you may get a calculator with sliders. OpenAI's own headline for the release was "GPT-6 and Intelligent UI for everyone."
What changed on October 7
Two things shipped together in the Chat tab:
- A new default model. Chat now runs on GPT-6. Paying users get GPT-6 Sol; Free and Go users get GPT-6 Luna, the lighter, cheaper model in the family. Until now, the regular Chat tab defaulted to GPT-5.6 Sol (paid) and GPT-5.6 Luna (Free and Go). The GPT-6 Sol and Luna models themselves are not new: they launched on September 22 in ChatGPT Work, Codex, and the API. What's new is that they now power everyday chat.
- Intelligent UI. The model decides, per question, whether text or an interface would answer it better. Per The Decoder, comparisons may appear side by side, explanations can become interactive charts, and you can ask for small tools inside the chat, such as a savings calculator. iClarified reports that interface elements appear progressively as the answer is generated, and that simple requests still get plain text.
OpenAI also says GPT-6 can start answering while it is still reasoning, adding detail in stages. Per iClarified, OpenAI's figure is that GPT-6 Instant starts responding to questions that need a web search 44% sooner on average than GPT-5.6 Instant. That is OpenAI's internal measurement, not an independent benchmark.
Who gets it, and when
| Plan | Chat model | Intelligent UI from |
|---|---|---|
| Plus, Pro, Business | GPT-6 Sol | October 7, 2026 (rolling out) |
| Enterprise | GPT-6 Sol | October 7, 2026, depending on admin settings |
| Free, Go | GPT-6 Luna | October 8, 2026 (rolling out) |
These details come from OpenAI's announcement as reported by TechCrunch, iClarified, XDA Developers, and The Decoder, which agree with each other. OpenAI's help center had not confirmed plan-level details when we checked on launch day, so treat the dates as "starting" dates. Gradual rollouts can take several days to reach every account.
A few things this release does not change:
- ChatGPT Work and Codex keep their current models. OpenAI says the release covers Chat only.
- GPT-6 Astra keeps its existing access rules: in regular chat (shown as "GPT-6 Pro" in the picker) on Pro, Business, and Enterprise, and only inside Work and Codex on Plus. Our GPT-6 Astra guide has the plan-by-plan detail.
- Prices. No plan prices changed with this release. See ChatGPT pricing explained for current plans.
Can you turn Intelligent UI off?
Not completely, as far as OpenAI has said. TechCrunch reports that the feature is customizable: as with other aspects of ChatGPT's personality, users who don't want so many visuals in their responses will be able to dial them back. That is a "less" control, not an "off" switch.
We could not confirm the exact name or location of that setting from OpenAI's own documentation on launch day. Some third-party guides name a specific menu path; we haven't included one because OpenAI hasn't confirmed it. If you prefer text answers in the meantime:
- Ask in the prompt. "Answer in plain text only, no charts or interactive elements" works for a single question.
- Put it in custom instructions. Adding the same line to ChatGPT's custom instructions applies it to every new chat. It is a request to the model rather than a hard switch, so expect the occasional visual anyway.
- Check Settings after the rollout reaches you. Look under Personalization, where ChatGPT's personality controls already live, for a visuals option.
What it means if you use ChatGPT for work
The upside is real. For explaining something to a non-expert, a clickable diagram beats three paragraphs. A quick interactive model of a pricing scenario, a loan, or a project timeline can help you think, and it saves a trip to a spreadsheet for rough estimates.
The risk is that polish looks like proof. A chart drawn by an AI is only as accurate as the numbers the model put into it, and a calculator is only as accurate as the formula it wrote. Neither is visible by default. Before a ChatGPT chart or calculator goes into a deck, an email, or a client conversation:
- Ask it to show the underlying data and the formula as a plain table.
- Check those against your own source, especially any figure it found through web search.
- Rebuild anything important in your own spreadsheet or charting tool, where you control the inputs.
Need editable text? If you plan to paste an answer into a document, ask for a plain-text version rather than relying on the interactive one.
At work, check with your admin. On Enterprise, access depends on administrator settings, so if you don't see it, that may be deliberate. The usual rules still apply: don't paste confidential data into a tool your employer hasn't approved.
Should you change how you use ChatGPT?
Not much. Your plan, your prices, and the Work and Codex tabs are the same as last week. The practical changes are small: try a visual answer the next time you need to explain something, ask for plain text when you need to copy and edit, and verify the numbers before any chart leaves your screen.
If you want a broader look at how ChatGPT compares with the alternatives for professional work, see ChatGPT vs Claude vs Gemini for professionals.
Sources
- OpenAI, "GPT-6 and Intelligent UI for everyone" (October 7, 2026): https://openai.com/index/gpt-6-for-everyone
- TechCrunch, "ChatGPT is getting a lot more visual, with the launch of a new interface" (October 7, 2026): https://techcrunch.com/2026/10/07/chatgpt-is-getting-a-lot-more-visual-with-the-launch-of-a-new-interface/
- The Decoder, "ChatGPT with GPT-6 ditches mostly text output for interactive UI with charts, buttons, and mini apps" (October 7, 2026): https://the-decoder.com/chatgpt-with-gpt-6-ditches-mostly-text-output-for-interactive-ui-with-charts-buttons-and-mini-apps/
- iClarified, "OpenAI Rolls Out GPT-6 and 'Intelligent UI' in ChatGPT" (October 7, 2026): https://www.iclarified.com/102657/openai-rolls-out-gpt-6-and-intelligent-ui-in-chatgpt
- XDA Developers, "GPT-6's new feature adds interactive elements to your chat, even if you're a free user" (October 7, 2026): https://www.xda-developers.com/gpt-6s-new-feature-adds-interactive-elements-to-your-chat/
- OpenAI, "Introducing GPT-6 Sol and Luna" (September 22, 2026): https://openai.com/index/introducing-gpt-6-sol-and-luna/
See Claude set up for your job
Skip the theory — pick your profession and get the real workflows, ready-to-use prompts, and exact setup for your work.
Set up AI for your job — free, in about 2 minutes
Pick your profession and get your first working AI tool, a step-by-step guide, and a $0 plugin to take home. No credit card.
Get my free setupSee Claude set up for your job
Real workflows and ready-to-use prompts, profession by profession.
Frequently asked questions
What is Intelligent UI in ChatGPT?+
Intelligent UI is a change to how ChatGPT presents answers, launched with GPT-6 in the regular Chat tab on October 7, 2026. Instead of mostly text, a response can include interactive charts, diagrams, tappable buttons, forms, and small tools such as a savings calculator or a bill splitter. ChatGPT decides when a visual would help; simple questions still get plain text.
When do I get Intelligent UI and GPT-6 in ChatGPT?+
According to OpenAI's announcement as reported by TechCrunch, iClarified, and The Decoder, the rollout started globally on October 7, 2026 for Plus, Pro, Business, and Enterprise users, and reaches Free and Go users on October 8. Paid plans run on GPT-6 Sol in Chat; Free and Go run on GPT-6 Luna. Enterprise access depends on your workplace administrator's settings. Rollouts are gradual, so it may take a few days to appear in your account.
Can I turn off Intelligent UI?+
You can reduce it, but OpenAI has not described a full off switch. TechCrunch reports that, as with ChatGPT's other personality settings, users who don't want so many visuals will be able to dial them back. OpenAI's help center had not published the exact setting when we checked on launch day. In the meantime, asking for 'plain text only, no charts or interactive elements' in your prompt or custom instructions is a reasonable workaround.
Does this change ChatGPT Work or Codex?+
No. OpenAI says this release covers the Chat tab only and does not change the models that power ChatGPT Work or Codex. GPT-6 Sol and Luna have been available in Work, Codex, and the API since September 22, 2026, and GPT-6 Astra (shown as 'GPT-6 Pro' in the picker) keeps its existing plan rules.
Can I trust the charts and calculators ChatGPT builds?+
Treat them like any other AI output: useful for exploring, not proof. A chart is only as accurate as the numbers the model put into it, and an interactive calculator is only as accurate as the formula it wrote. Before reusing one at work, ask ChatGPT to list the underlying data and formula as plain text and check them against your own source.
Related Guides
Does ChatGPT Watermark Your Text Now? What OpenAI's EU Watermark Means (October 2026)
On October 5, 2026, OpenAI said it will add an invisible watermark, called textGrain, to ChatGPT and Codex text generated in the EU over the coming weeks, and let API customers anywhere opt in. Here's who it covers, what the mark can and can't show, who can detect it, and how it compares with Claude's worldwide watermark.
Is Gemini Still Free? What Free and AI Plus Users Lose on October 9 (October 2026)
Gemini is still free, but starting October 9, 2026, people without a Google AI plan can only use Flash-Lite, Google's smallest model, and lose Flash and Pro. AI Plus subscribers lose Pro on a date Google will email them. Google has given conflicting wording on whether AI Pro gets Deep Think. Here's what changes on each plan and what to do before the switch.
Can AI Fire You in California? What the New Workplace AI Laws Mean (October 2026)
On September 30, 2026, Governor Newsom signed California's No Robo Bosses Act (SB 947) and three related workplace AI laws. Starting July 1, 2027, an employer can't fire or discipline you based on an AI system alone, and must tell you when AI was used. Here's what each law does, when it starts, and what to do if you work in or manage people in California.