Open Settings
Open ChatGPT and go to Settings from your account or profile menu.
Control your memory
How to turn ChatGPT memory on or off.
ChatGPT memory lives in one place — Settings → Personalization → Memory — and it has two independent switches. This guide shows you exactly where to find them, what each one does, and the important detail most people miss: turning memory off is not the same as deleting it.
Quick answer
Two toggles, controlled separately
Memory isn't a single on/off switch. There are two toggles in Settings → Personalization → Memory, and they behave differently when you turn them off.
| Toggle | What it controls | What happens when you turn it off |
|---|---|---|
| Reference saved memories | Whether ChatGPT uses the explicit facts it has stored about you. | ChatGPT stops using stored facts. Per OpenAI, this also turns off "Reference chat history." Your saved memories are not deleted. |
| Reference chat history | Whether ChatGPT draws on patterns from your past conversations. | ChatGPT stops drawing on past chats, while your saved memories can still be used (if that toggle stays on). |
| Temporary Chat | A per-conversation way to skip memory entirely without changing settings. | Not applicable — it's a mode you start per chat. Nothing is read from or written to memory. |
The exact labels and behavior can change. Always confirm on OpenAI's Memory FAQ and Data Controls FAQ.
Step by step
Turn ChatGPT memory on or off
The path is the same on desktop and mobile, though the menu names may differ slightly. Check OpenAI's help center if your screen looks different.
Open Personalization → Memory
In Settings, choose Personalization, then open the Memory section where the toggles live.
Toggle "Reference saved memories"
Switch it off to stop ChatGPT using stored facts, or on to resume. Per OpenAI, turning this off also turns off chat history.
Toggle "Reference chat history"
With saved memories on, turn chat history on or off independently to control implicit recall from past chats.
Related: how memory works · saved vs chat history · delete memory · Temporary Chat
Important distinction
Turning memory off vs deleting it
| Question | What to know |
|---|---|
| Does off delete my memories? | No. Turning off "Reference saved memories" stops ChatGPT from using them but does not auto-delete them. To remove them, use delete memory. |
| Is my data still stored? | Yes — memory sits on OpenAI's servers tied to your account. Every message is processed server-side regardless of your toggle settings. |
| How do I have a memory-free chat? | Start a Temporary Chat — no settings change needed; it doesn't read or write memory. |
| Why are the toggles missing? | The feature rolls out gradually and an admin can disable it on Business plans. See memory not working. |
If memory worries you
Use AI without locking all your context to one provider
Memory is convenient, but it concentrates your personal context inside one company's servers. If you'd rather spread your usage — and pick which model sees which prompt — a multi-model workspace gives you that choice while you keep sensitive topics in memory-free sessions.
All-in-one
MultipleChat AI
multiplechat.aiUse ChatGPT, Claude, Gemini and other models in one place — choose where each prompt goes instead of feeding everything to a single assistant.
Privacy-first: MultipleChat doesn't save your chats to memory and doesn't share your data with model providers or let them train on it. Other privacy-focused options include Duck.ai, Proton Lumo, Brave Leo and Kagi Assistant; for full local control, self-hosted tools like Ollama or Jan keep everything on your device.
OpenAIChatGPT
chatgpt.comOffers Temporary Chat (no history, not used for training), a training opt-out under Settings → Data Controls, and editable memory. By default, consumer chats may be used to improve models unless you opt out — verify on OpenAI's help center.
AnthropicClaude
claude.aiAnthropic gives you data and training controls and has historically taken a privacy-conscious stance on consumer chats, but its training and retention settings have changed over time — check your current privacy settings in the app.
GoogleGemini
gemini.google.comGemini Apps Activity lets you pause history and delete past activity, but sampled conversations can be reviewed by humans, so avoid sharing confidential information. Review your Activity controls.
MicrosoftCopilot
copilot.microsoft.comMicrosoft 365 Copilot (business) doesn't use your organization's data to train models and adds Enterprise Data Protection; consumer Copilot has a privacy dashboard to review and delete your history. Check current Microsoft policies.
PerplexityPerplexity
perplexity.aiPerplexity has an "AI data retention" setting you can switch off so your searches aren't used to improve its models, plus account-level data controls. Confirm the current options in settings.
All guides
ChatGPT memory: every guide
How memory worksThe technical walkthrough.
Saved vs chat historyThe two layers compared.
Turn memory on/offManage the settings.
Delete memoryClear individual or all.
Memory & privacyRisks and how to reduce them.
Memory & trainingIs it used to train models?
Temporary ChatMemory-free conversations.
Memory not working?Troubleshooting steps.
Memory limitsHow much it can hold.
Team & EnterpriseMemory and data controls.
Memory vs custom instructionsWhat's the difference?
Memory FAQEvery common question.
FAQ
Turning memory on or off — quick answers
Where the toggles are, what they do, and how on/off differs from deleting.
Where do I turn ChatGPT memory on or off?
Open Settings → Personalization → Memory. That panel has the two memory toggles: "Reference saved memories" and "Reference chat history." Confirm the exact wording on OpenAI's help center, since the interface changes.
What are the two memory toggles?
"Reference saved memories" controls whether ChatGPT uses the explicit facts it has stored about you. "Reference chat history" controls whether it can draw on patterns from your past conversations. They are independent toggles you control separately.
Does turning off saved memories also turn off chat history?
Per OpenAI, turning off "Reference saved memories" also turns off "Reference chat history." If you want to keep saved memories but stop the implicit recall, leave saved memories on and turn off chat history. Verify current behavior on OpenAI's help center.
Does turning memory off delete my saved memories?
No. Turning off "Reference saved memories" stops ChatGPT from using stored facts, but it does not auto-delete them. To remove them you must delete the memories separately in "Manage memories."
How do I turn memory back on?
Go back to Settings → Personalization → Memory and switch the toggles on again. Any memories that were not deleted while it was off remain available once you re-enable saved memories.
Can I have a memory-free chat without changing my settings?
Yes. Start a Temporary Chat from the model or name menu. Temporary Chats do not read or create memories and do not appear in your history, so you can keep memory on for normal use and switch to a memory-free session when you need one.
Why don't I see the memory toggles?
Memory features roll out gradually and may not be available on every plan or region, and a Business or Enterprise admin can disable them. If the toggles are missing, check whether you are on the right account and review OpenAI's current availability notes.
Where is memory stored after I turn it off?
Memory is stored on OpenAI's servers tied to your account, not on your device. Turning the toggle off stops the data from being used, but it does not by itself remove what is stored; deletion and retention are described on OpenAI's help center.
Does memory work across devices once it is on?
Because memory is tied to your account on OpenAI's servers, it generally follows you across devices when you are signed in to the same account. If memory seems absent on one device, confirm you are logged into the correct account.