What is a Context Window?
The maximum amount of text a language model can consider at one time, measured in tokens.
Pronunciation: /ˈkɒntekst ˈwɪndəʊ/
Context Window explained in plain English
The context window is the amount of text an AI model can "see" at once — including your prompt, any retrieved documents, and the model's response. It is measured in tokens.\n\nA larger context window means the model can work with longer documents, maintain longer conversations, and consider more information when generating a response.
Analogy
The context window is like a desk surface. A small desk (small context window) means you can only spread out a few pages at a time. A large desk lets you lay out an entire book while you work.
Example
Claude can process a 200,000-token context window — enough to analyse an entire novel or a large codebase in a single conversation.
How is Context Window used?
Context window size is a key specification when choosing a model. Applications processing long documents, legal contracts, or extended conversations need models with larger context windows.
Common misconceptions about Context Window
History
Related terms
People also read
- LLM
A type of AI model trained on vast amounts of text to understand and generate human language.
- Token
The basic unit of text that AI language models process, which may be a word, part of a word, or punctuation.
- AI slop
Output from a generative AI system that favors quantity over quality.
- Chain-of-Thought Prompting
Asking an AI to show its reasoning step by step before giving a final answer, which often improves accuracy on complex tasks.
- Confabulation
When an AI produces a confident, fluent answer that sounds true but is factually wrong — generating plausible language without a reliable link to reality.
- Embedding
A numerical representation of text, images, or other data that captures semantic meaning.
- Fine-tuning
The process of further training a pre-trained AI model on specialised data to improve performance on specific tasks.
- generative AI
An emerging transformative field with no formal definition.
- GPT
A family of large language models developed by OpenAI that generate human-like text.
- hallucination
The production of plausible-seeming but factually incorrect output by a generative AI model that purports to be making an assertion about the real world.