# How does ChatGPT separate current and legacy models in its model picker? Lazyweb publishes a public search API over its indexed pages; the guide is at https://www.lazyweb.com/agent-access.md. Source: https://www.lazyweb.com/research/chatgpt-model-picker-progressive-disclosure Source observed: 2026-09-14T19:15:40.856Z Last checked: 2026-09-15T19:48:43.277+00:00 Indexed: 2026-09-14T20:14:35.348+00:00 --- # How does ChatGPT separate current and legacy models in its model picker? In our January 2026 capture, the first ChatGPT menu presents four GPT-5.2 choices with short descriptions. A separate **Legacy models** row opens a longer, scrollable list. This keeps the primary decision compact while retaining access to older options. It is a historical UI example, not a list of models available today. [1](https://www.lazyweb.com/research/chatgpt-model-picker-progressive-disclosure#cite-1) **By Ali Abouelatta · Lazyweb Research · Published 2026-09-09 · Reviewed September 2026** ![January 2026 primary menu: four described GPT-5.2 options and a Legacy models row](https://zlfyzdmohcskkucuunmk.supabase.co/storage/v1/object/public/screenshots/prod11_chatgpt/backlog/2026_01_13_10-34-32_02C5AA88.png) ![January 2026 expanded legacy-model list with a scrollbar](https://zlfyzdmohcskkucuunmk.supabase.co/storage/v1/object/public/screenshots/prod11_chatgpt/backlog/2026_01_13_10-34-34_117A3DFA.png) Real in-market screens from **ChatGPT** — tracked by Lazyweb Research. ## What the two screenshots show The first screen groups **Auto**, **Instant**, **Thinking**, and **Pro** beneath the **GPT-5.2** heading. **Auto** carries a checkmark. Each option includes a short explanation of its intended behavior, and a divider separates **Legacy models** from the primary choices. [1](https://www.lazyweb.com/research/chatgpt-model-picker-progressive-disclosure#cite-1) The second screen shows an expanded legacy list with several model generations and a visible scrollbar. The conversation composer remains visible behind the menu. These are two captured menu states, not a complete recording of selection and response behavior. [1](https://www.lazyweb.com/research/chatgpt-model-picker-progressive-disclosure#cite-1) ## The design decision There are two jobs: choosing a behavior for the next response and deliberately returning to an older model. The captured hierarchy gives those jobs separate levels. Our interpretation is that this can reduce the number of equally prominent choices; the screenshots do not measure whether people choose faster. [1](https://www.lazyweb.com/research/chatgpt-model-picker-progressive-disclosure#cite-1) ## When to use the pattern Consider a short primary list when a product has a few common modes and many specialist or older options. Give each primary choice a meaningful description, expose selection state, and label the secondary collection clearly. Do not copy a historical model roster into a current product. This is design guidance, not an observed experiment result. **Methodology.** We inspected two public screenshots from one historical ChatGPT mobile flow individually. We make no current model-availability, interaction-timing, or conversion claim. ## Sources & citations 1. **ChatGPT model-picker capture** — [Open source](https://www.lazyweb.com/flow/chatgpt/model-picker). Two public screenshots; page metadata updated January 2026. Visually inspected September 9, 2026. [↩](https://www.lazyweb.com/research/chatgpt-model-picker-progressive-disclosure#ref-1) Source: **Lazyweb Research** — proprietary analysis of real, in-market app screens. Cite as _Lazyweb Research, 2026-09-09_. ## Explore the evidence - [ChatGPT model picker](https://www.lazyweb.com/flow/chatgpt/model-picker) — Two captured screens · January 2026 - [Claude feature-access prompt](https://www.lazyweb.com/flow/claude/locked-feature-paywall) ## Related questions - [What comes between sign-in and the trial reminder in Cal AI’s paywall flow?](https://www.lazyweb.com/research/cal-ai-sign-in-trial-reminder-sequence) [More in AI interface decisions](https://www.lazyweb.com/research/category/ai-interface-decisions) · [More research](https://www.lazyweb.com/research) --- ## Related searches on Lazyweb Each link returns Markdown search results. - [How does ChatGPT separate current and legacy models in its model picker?](https://www.lazyweb.com/s/how-does-chatgpt-separate-current-and-legacy-models-in-its-model-picker.md?trace=t_3bb929fdaf0e) - [What the two screenshots show](https://www.lazyweb.com/s/what-the-two-screenshots-show.md?trace=t_3bb929fdaf0e) - [The design decision](https://www.lazyweb.com/s/the-design-decision.md?trace=t_3bb929fdaf0e) - [When to use the pattern](https://www.lazyweb.com/s/when-to-use-the-pattern.md?trace=t_3bb929fdaf0e) - [Sources & citations](https://www.lazyweb.com/s/sources-citations.md?trace=t_3bb929fdaf0e) [Tool guide and examples](https://www.lazyweb.com/agent-access.md) · [OpenAPI](https://www.lazyweb.com/api/public/v1/openapi.json) · [Page TLDR form](https://www.lazyweb.com/agent-tools/page-tldr?question=Read+a+compact+extract+of+How+does+ChatGPT+separate+current+and+legacy+models+in+its+model+picker%3F&url=https%3A%2F%2Fwww.lazyweb.com%2Fresearch%2Fchatgpt-model-picker-progressive-disclosure). Opening a form does not execute a tool.