# Context window

> A context window is the maximum amount of text, measured in tokens, that a language model can read and write in one request, counting instructions, documents and its reply.

- Page: https://methodcrew.com/glossary/context-window
- Last updated: 2026-10-28
- Publisher: [The Method Crew](https://methodcrew.com/)
- Also known as: context length

## How it works

Everything a model works with on a given request has to fit in the window: the system prompt, the conversation so far, retrieved documents, tool definitions, tool results and the answer it writes. A token is a piece of a word; in English, 1,000 tokens is roughly 750 words. Frontier models in late 2026 accept hundreds of thousands of tokens, and several accept 1 million or more.

The model keeps no memory between requests. A chatbot that "remembers" earlier messages is resending them each time, which is why long conversations get slower and more expensive.

## How businesses use it

Large windows make some jobs simple: compare 2 contracts in full, summarize a long call transcript, or check a 200-page RFP against a checklist in 1 pass. For one-off analysis that is often the right approach.

For an assistant that answers questions across thousands of documents, retrieval is still the better design. [RAG](https://methodcrew.com/glossary/retrieval-augmented-generation) sends only the relevant passages, so each request costs less and returns faster.

Context also limits [AI agents](https://methodcrew.com/glossary/ai-agent). Every tool definition and tool result takes up space, so an agent with 40 tools and a long task can fill its window before it finishes. Well-built [custom agents](https://methodcrew.com/services/custom-ai-agents) trim old tool output and summarize as they go.

## Where it goes wrong

A bigger window does not mean the model reads all of it equally well. The [Lost in the Middle](https://arxiv.org/abs/2307.03172) study (Liu and colleagues, 2023) found that models used information at the start and end of a long input better than information buried in the middle. Test your own long-document tasks before trusting the advertised size.

Cost is the other trap. You pay for every input token on every request, so a prompt that pastes a 300-page manual into each question gets expensive quickly. Send only what the task needs, and keep standing instructions short enough that they do not crowd out the documents.

## Example (hypothetical)

Hypothetical: a 50-person law firm wants to check incoming NDAs against its playbook. Each NDA runs to about 6,000 tokens, so the whole agreement, the 3-page playbook and the instructions fit in 1 request, and this job needs no retrieval system.

## Related terms

- [Large language model (LLM)](https://methodcrew.com/glossary/large-language-model): A large language model is a neural network trained on huge volumes of text to predict the next token, which lets it write, summarize, classify and answer questions.
- [Retrieval-augmented generation (RAG)](https://methodcrew.com/glossary/retrieval-augmented-generation): Retrieval-augmented generation is a method where a system first searches your own documents for relevant passages, then gives them to a language model to answer from.
- [Chunking](https://methodcrew.com/glossary/chunking): Chunking is splitting documents into smaller passages before they are embedded and indexed, so a retrieval system can find and return the exact part that answers a question.
- [AI agent](https://methodcrew.com/glossary/ai-agent): An AI agent is a language model that chooses and calls tools in a loop, reading each result, until it finishes a task or hands off to a person.
- [Prompt engineering](https://methodcrew.com/glossary/prompt-engineering): Prompt engineering is writing and testing the instructions, examples and context given to a language model so it produces the output a task needs, consistently.

## Services where this matters

- [Custom AI agents and copilots](https://methodcrew.com/services/custom-ai-agents): Agents that look things up in your CRM or helpdesk and take the next step, with approvals. $15,000 to $90,000 per project.
- [RAG and knowledge systems](https://methodcrew.com/services/rag-knowledge-systems): Your documents turned into an assistant that cites its sources. $15,000 to $75,000 per project.

Full glossary: https://methodcrew.com/glossary