--- id: chatgpt-context-and-memory lang: en track: chatgpt title: "Context and memory" seoTitle: "ChatGPT context window, tokens and memory" description: "What a token is, what ChatGPT's context window holds, how it differs from memory, why long chats start to drift, and when it pays to start a fresh chat." part: working-smart partTitle: "Working smart" partOrder: 4 order: 1 level: Intermediate durationMinutes: 5 outcome: "Manage the context window and memory so long ChatGPT conversations stay sharp instead of drifting." summary: "The context window is ChatGPT's desk for one chat, measured in tokens. Memory is what it carries between chats. Keep the desk lean and the memory accurate, and long work stays sharp." draft: false updated: "2026-10-14" furtherReading: - title: "Understanding and counting tokens" url: "https://help.openai.com/en/articles/4936856-what-are-tokens-and-how-to-count-them" note: "OpenAI's own rules of thumb for what a token is." - title: "ChatGPT plans and pricing" url: "https://chatgpt.com/pricing/" note: "The context window per plan, for Instant and for thinking." - title: "Memory in ChatGPT" url: "https://help.openai.com/en/articles/8590148-memory-faq" note: "How memory works across chats, and how to manage it." - title: "Projects in ChatGPT" url: "https://help.openai.com/en/articles/10169521-projects-in-chatgpt" note: "Where long-running work belongs, covered in lesson 4.3." keywords: - ChatGPT context window - what is a token - ChatGPT token limit - ChatGPT memory vs context - ChatGPT conversation too long - when to start a new chat quiz: intro: "Five quick questions. Ace them all and you've got the window under control." passScore: 5 questions: - q: "What is a token, in plain terms?" options: - "One word, however long it is" - "A chunk of text, about four characters" - "One full message you send" - "A unit you pay for in your monthly subscription" answer: 1 explain: "ChatGPT reads text in tokens: roughly four characters each, so 100 tokens is about 75 English words. The window's size and much of your usage are counted in them." - q: "What is the difference between the context window and memory?" options: - "Two names for the same thing" - "Memory holds this chat; the window holds past chats" - "The window is on Free; memory on paid plans" - "The window is this chat; memory carries between chats" answer: 3 explain: "The window is the desk for one conversation. Memory is a separate store of saved details and chat history that ChatGPT can bring onto that desk when it seems relevant." - q: "Why can the same long chat feel roomier on a thinking level than on Instant?" options: - "Thinking models have a much larger context window" - "Thinking levels compress older parts of the chat as they go" - "Instant deletes older messages on purpose" - "Thinking levels also use your saved memories" answer: 0 explain: "The thinking levels get a much bigger context window than Instant. More room means more of the conversation and files fit at once. It still isn't endless." - q: "A long chat starts repeating itself and ignoring an early instruction. What's the smart move?" options: - "Keep going; it usually recovers" - "Turn memory off and continue in the same chat" - "Get a handoff summary, then start a fresh chat" - "Paste the whole conversation into a new chat" answer: 2 explain: "A tired window loses detail. Ask ChatGPT to sum up the decisions, the current draft and open questions, then start clean with that summary." - q: "Which of these actually leaves more room in the window?" options: - "Turning memory on for more context" - "Lean text files and only the apps the task needs" - "Turning on every plugin, just in case" - "Attaching the full PDF instead of a short text extract" answer: 1 explain: "Everything you bring in takes space: files, app results, the conversation itself. Lean material and only the tools you need leave room for the real work." pass: badge: "Part 4 started" title: "You run the window now, not the other way round." body: "Full marks. You know what a token is, how the window differs from memory, why long chats drift, and how to keep one sharp. Next up: skills and plugins, packaged ways to do a job the same way every time." retry: "Check the marked answers and give it another go. You've got this." --- > **Level:** Intermediate · **Reading time:** ~5 min > > **What you'll be able to do:** manage the context window and memory so long ChatGPT conversations stay sharp instead of drifting. In [lesson 2.5](/learn/chatgpt/getting-started/giving-chatgpt-context) you met two ideas: the **context window**, ChatGPT's working space for one chat, and **memory**, what it carries from chat to chat. We left the mechanics for later. Later is now. This one pays off fast. Once you can picture what fills the window, how memory feeds it, and why a long chat goes fuzzy, you stop fighting ChatGPT and start steering it. **The reward: sharper answers, fewer do-overs, and chats that don't fall apart at the two-hour mark.** ## First, a token ChatGPT doesn't read letters or whole words. It reads **tokens**: small chunks of text. OpenAI's own rule of thumb: a token is about **four characters**, or roughly **three-quarters of an English word**, so *100 tokens is about 75 words*. Other languages, Dutch included, often take a few more tokens for the same text.
What ChatGPT actually reads A short sentence split into token chunks, some whole words and some pieces of a word. A token is about four characters, so 100 tokens is about 75 English words. Illustration only; real splits vary. What ChatGPT actually reads Not letters, not words: tokens. Every chunk below is one token. Sum mar ise ·the ·quarter ly ·sales ·report . 9 tokens for 5 words. Rule of thumb: a token is about 4 characters, so 100 tokens is about 75 words. (Illustration; real splits vary.)
Why care? Because **tokens are the unit everything is counted in.** The window's size is in tokens. Long inputs take longer to process. And on plans with usage-based allowances, like Work and Codex, bigger jobs use more. So "how many tokens is this?" really means "how much space and time will it take?" ## What the window actually holds Picture your desk. The **context window** is the desk surface: everything ChatGPT can look at while it answers. Not your whole archive, just what is on the desk *right now*, in *this* chat. Four things share that surface: - **The files you attached.** Uploads, pasted text, results pulled in from apps. - **The conversation so far.** Every message, yours and ChatGPT's. - **What memory brings in.** Your custom instructions and any saved memories or past-chat details ChatGPT judges relevant. - **The reply being written.** Space is always kept for the answer. **How big is the desk?** It depends on your plan *and* your setting. On Plus, Instant has about **54,000 tokens**, while the thinking models get about **256,000**, roughly 320 pages of text. Pro goes to 128,000 and 400,000. OpenAI doesn't publish one number for Business, and it varies by model, so the practical rule is the same everywhere: **thinking levels give you a much bigger desk than Instant.** It still isn't endless. ## Window versus memory People mix these up, and it causes real confusion. **The window is the desk; memory is a filing cabinet next to it.** The desk is wiped clean when you start a new chat. The filing cabinet isn't: saved memories, chat history, and your custom instructions sit there between chats, and ChatGPT pulls the relevant bits onto the desk when it answers. That is why a brand-new chat can still "know" your role.
The desk and the filing cabinet Left: the context window, the desk for this chat. It holds files, the conversation, what memory brings in and the reply, is measured in tokens, and is cleared by a new chat. Right: memory, the filing cabinet between chats, with saved memories, chat history and custom instructions, managed in Settings. The desk and the filing cabinet Context window THE DESK: THIS CHAT Files and pasted text The conversation so far What memory brings in Room for the reply Cleared by a new chat. Memory THE CABINET: BETWEEN CHATS Saved memories Chat history Custom instructions Managed in Settings Survives a new chat. Keep it accurate. vs
Two consequences. First, **a new chat clears the desk but not the cabinet**, so starting fresh doesn't lose who you are. Second, **whatever memory brings in also takes desk space**, and if it's out of date, it quietly steers the answer. Lesson 2.5's habit, checking the memory summary now and then, keeps the cabinet honest. ## Why long chats drift The desk is big, but it fills. As a conversation grows, early details get harder for the model to keep track of, and in the end ChatGPT simply stops: *"You've reached the maximum length for this conversation, but you can keep talking by starting a new chat."* Well before that, you may feel the drift: - It **repeats** a point it already made. - It **forgets** an instruction you gave near the top. - It gets **blander** than it was an hour ago. - It **contradicts** something you agreed earlier. There's a subtler version too. Even below the limit, a cluttered window makes it harder to find the part that matters, the way a crowded desk buries the one page you need. *What is on the desk matters as much as how much fits.* ## When to start fresh, and how to carry work over The fix is a habit: **one topic per chat, and start fresh when the topic changes or the answers start slipping.** A new chat is a clean desk. You don't have to lose the thread. **Hand the work over on purpose:** ``` Before we stop, write a short handoff I can paste into a new chat. Cover: what we've decided, the current draft, and the open questions. Keep it tight. ``` Paste that into a fresh chat and carry on. For work you return to often, put it in a **project** ([lesson 4.3](/learn/chatgpt/working-smart/projects)), so the files and instructions are waiting next time. ## Keep the window working for you - **Feed it lean material.** Plain text and **Markdown** carry the same words as a heavy PDF or styled Word file for far less space. - **Bring in only what the task needs.** Every file, app result, and search adds to the desk. Mention the one app you need instead of pulling from five. - **Pick the level for the job.** Long documents and big analyses fit better on a thinking level; quick tasks don't need the extra room. - **Keep memory accurate.** Delete memories that are wrong or outdated, or use a Temporary Chat for one-offs that shouldn't feed it. **The rule of thumb:** a clean, focused chat beats a giant sprawling one every time. ## Where this goes next You now hold the levers that decide how well any long piece of work goes: **what you put on the desk, what the cabinet brings in, and when you clear it.** Next in Part 4 we start reusing your best work: **skills and plugins** package a job so ChatGPT does it the same way every time, and **projects** give ongoing work a home. ## Try it Take a long chat you already have, or push a fresh one on a real task until it starts to slip. Then test the handoff: paste the summary prompt above, open a new chat, paste the summary in, and ask your next question there. Last, open **Settings, Personalization, Memory** and read what ChatGPT keeps about you. Anything that would mislead a fresh chat? Fix it. **Clean desk, honest cabinet: that's the whole lesson.** *(General exercise. Role and industry versions come once accounts are in.)* ## Key terms [Context window](/glossary#context-window), [Token](/glossary#token), [Memory](/glossary#chatgpt-memory), [Context](/glossary#context), [Project](/glossary#chatgpt-project), [Markdown](/glossary#markdown)