---
id: context-and-tokens
lang: en
title: "Context and tokens"
seoTitle: "Context windows & tokens explained"
description: "What a token is, what the context window holds, why long chats drift, and when to start fresh, so you get more from every conversation with Claude."
part: working-smart
partTitle: "Working smart"
partOrder: 4
order: 1
level: Intermediate
durationMinutes: 6
outcome: "Manage the context window so long conversations stay sharp instead of drifting."
summary: "The context window is Claude's desk: everything it can see at once, measured in tokens. Keep it lean and one topic per chat, and long work stays sharp."
draft: false
updated: "2026-07-26"
furtherReading:
- title: "How large is the context window on paid Claude plans?"
url: "https://support.claude.com/en/articles/8606394-how-large-is-the-context-window-on-paid-claude-plans"
note: "The current per-model sizes for chatting in claude.ai, kept up to date by Anthropic."
- title: "How do usage and length limits work?"
url: "https://support.claude.com/en/articles/11647753-how-do-usage-and-length-limits-work"
note: "The difference between running out of space (length) and running out of quota (usage)."
- title: "Context windows (Claude docs)"
url: "https://docs.claude.com/en/docs/build-with-claude/context-windows"
note: "How the window fills up and why very long contexts lose focus ('context rot')."
- title: "Effective context engineering for AI agents"
url: "https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents"
note: "Anthropic on why curating what goes in context beats simply adding more."
keywords:
- context window
- what is a token
- AI token limit
- long chat AI
- AI memory limit
- 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:
- "A password Claude needs to start a chat"
- "A small chunk of text (roughly four characters, about three-quarters of a word) that Claude reads and counts"
- "One full message you send"
- "A credit that pays for your subscription"
answer: 1
explain: "Claude reads text in tokens: small chunks of about four characters, or roughly three-quarters of a word. Everything is measured in them: the window's size, the speed, and the cost."
- q: "During a single chat, what sits in the context window at once?"
options:
- "Everything on the internet"
- "Only your most recent message"
- "Your files, the whole conversation so far, and the reply Claude is writing"
- "Nothing; Claude has perfect memory"
answer: 2
explain: "The window is Claude's working memory for one chat. It holds the files you added, every message so far, and the answer being written. All of it counts against the limit."
- q: "Why does a very long chat start to drift, repeat itself, or forget an earlier instruction?"
options:
- "Claude gets tired"
- "The window fills up, so Claude summarises the earlier parts and some detail is lost"
- "Your internet slows down"
- "It never happens"
answer: 1
explain: "As a chat nears the limit, Claude summarises the earlier messages to keep going. Summaries are shorter than the real thing, so fine detail can slip. That is what drift feels like."
- q: "You want to carry a long piece of work into a fresh chat. What is the smart move?"
options:
- "Copy and paste every single message across"
- "Do nothing; Claude remembers across chats automatically"
- "Ask for a short handoff summary (decisions, current draft, open questions), then paste that into the new chat or a project"
- "Start over from scratch and hope for the best"
answer: 2
explain: "Ask Claude to sum up what matters, then hand that summary to a fresh chat. You keep the thread without dragging the whole heavy history along."
- q: "Which of these actually frees up room in the window?"
options:
- "Typing faster"
- "Turning off tools and connectors you are not using, and feeding lean files like .md instead of heavy PDFs"
- "Using more exclamation marks"
- "Asking Claude to be brief"
answer: 1
explain: "Tools and connectors are token-hungry, and a PDF is read as images, so both eat space. Switch off what you do not need and prefer lean text. More room left means sharper 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, what the window holds, why long chats drift, and how to keep one sharp. Next up: Claude Skills, packaged instructions that do a job the same way every time."
retry: "Check the marked answers and give it another go. You've got this."
---
> **Level:** Intermediate ยท **Reading time:** ~6 min
>
> **What you'll be able to do:** manage the context window so long conversations stay sharp instead of drifting. *(Last checked: July 2026.)*
In lesson 2.5 you met the **context window**: Claude's working memory for a single chat. We left the mechanics for later. Later is now.
This one pays off fast. Once you can picture what fills the window and why a long chat goes fuzzy, you stop fighting Claude and start steering it. **The reward is simple: sharper answers, fewer do-overs, and chats that do not fall apart at the two-hour mark.**
## First, a token
Claude does not read letters or whole words. It reads **tokens**: small chunks of text. A token is about four characters, or roughly three-quarters of a word. So *100 tokens is about 75 words*, and a tidy page of text is somewhere near 500 tokens.
Why care about a unit of text? Because **tokens are the currency of everything.** The window's size is counted in tokens. Cost is counted in tokens. Speed tracks the token count too: more tokens in, more to chew through, longer to answer. So "how many tokens is this?" is really "how much space, money, and time will it take?"
## What the window actually holds
Picture your desk. The **context window** is the desk surface: everything Claude can look at while it works. It is not a filing cabinet of all your past chats, just what is on the desk *right now*, in *this* chat.
Three things share that surface:
- **The files you added.** Uploads, pasted text, project material.
- **The whole conversation so far.** Every message, yours and Claude's, back to the top.
- **The reply being written.** A slice is always kept clear for the answer, so the space you can fill is a bit smaller than the full number.
**How big is the desk?** On paid plans, chatting in claude.ai, it runs from **200,000 tokens up to 1,000,000**, depending on the model you pick. The newest model reaches the full million; most sit at 200,000. To put a million tokens in human terms, that is roughly 750,000 words, or a couple of thick books. It sounds endless. It is not, and here is why that matters.
## Why long chats drift
The desk is big, but it fills. When a chat nears the limit, Claude does something sensible: it **summarises the earlier parts** to make room, then keeps going. Your full history is still saved, but what Claude is *actively holding* becomes a shorter summary of the start plus the recent detail. (On paid plans this is automatic, as long as file creation is switched on. You might catch Claude "organising its thoughts" mid-chat; that is the tidy-up at work.)
A summary is smaller than the real thing, so **fine detail can slip.** That is what drift feels like from your side:
- It **repeats** a point it already made.
- It **forgets** an instruction you gave near the top.
- It gets **blander**, or a touch vaguer, than it was an hour ago.
- It **contradicts** something agreed earlier.
There is a subtler version too. Even below the limit, a very long, cluttered window makes it harder for Claude to find the part that matters, the way a crowded desk buries the one page you need. Anthropic calls this **context rot**: more stuff in the window is not always better. *What is in it matters as much as how much fits.*
## When to start fresh, and how to carry work over
The fix is not a trick. It 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, the whole window back at your disposal.
The worry, of course, is losing the thread. You do not have to. **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.
```
Take that summary, open a fresh chat, paste it in, and carry on. You keep the thread and drop the dead weight. For anything you return to often, put the summary in a **project** instead (that is lesson 4.3), so it is waiting for you next time.
## Keep the window working for you
A few small moves leave more room for the real work:
- **Feed it lean material.** As lesson 2.5 warned, a PDF is read as images and a Word file carries hidden styling, so both weigh a lot. Plain text and **Markdown** carry the same words for a fraction of the space. When you control the format and the material is big or reused, prefer `.md` or `.txt`.
- **Switch off what you are not using.** Web search, connectors, and extra tools are token-hungry just by being switched on. Turn off the ones this chat does not need.
- **Lower the effort, or turn off extended thinking**, for routine work. Both spend tokens you may not need for a quick task.
- **Use projects for big reference sets.** A project loads only the relevant slice of your files into the window rather than the whole pile, so you can lean on far more material without clogging the desk. More on that in lesson 4.3.
**The rule of thumb:** a clean, focused chat beats a giant sprawling one every time. Give Claude what the task needs, and not much more.
## Where this goes next
You now hold the two levers that decide how well any long piece of work goes: **what you put in the window, and when you clear it.** That is the quiet skill behind every power user.
Next in Part 4 we stop managing single chats and start reusing your best work. **Claude Skills** package a set of instructions so Claude does a job the same way every time. **Projects** keep files, context, and chats together. Both build straight on what you just learned.
## Try it
Open a long chat you already have, or a fresh one you push for a while on a real task, until you can feel it start to slip: repeating itself, forgetting an early instruction, or going vague.
Now test the handoff. Paste in the summary prompt above, take what Claude gives you, and start a new chat with it. Ask your next question there. Notice how the clean window answers sharper than the tired one did. **That gap is the whole lesson: same task, better result, just because you cleared the desk.**
*(General exercise. Role and industry versions come once accounts are in.)*
## Key terms
[Context window](/glossary#context-window), [Token](/glossary#token), [Context](/glossary#context), [Project](/glossary#project), [Markdown](/glossary#markdown)