Context Window is the maximum amount of text (measured in tokens) that a language model can consider at one time. Everything within the window is what the model can “see” and remember during a conversation.
What it means in plain English
A model does not have unlimited memory. The context window is its working memory: the span of text — your prompt plus the conversation so far, and any documents you provide — that it can take into account when generating a response. If a conversation grows longer than the window, the earliest parts fall out of view and the model effectively forgets them. Larger context windows let a model work with more information at once.
It is one of the most practically important specifications of a model.
A simple example
If you paste a very long document into a chatbot and its context window is too small, it can only “read” the portion that fits. Ask about something in the part that did not fit, and it will not know — because that text was never in its window.
Why it matters
The size of the context window determines how much a model can handle in one go — a short email or an entire book. Growing context windows is a major area of progress, because it expands what tasks a model can do, from analysing long documents to holding lengthy conversations.
Related terms
- Token — the unit the context window is measured in.
- Large Language Model — what has a context window.
- Prompt — part of what fills the context window.
Frequently asked questions
What is a context window in an LLM?
It is the maximum amount of text (measured in tokens) a language model can consider at once — including your prompt and its response. Content beyond the window is not “seen” by the model.
Why does context window size matter?
A larger context window lets a model work with more information at once — longer documents, more conversation history, or more retrieved data — which is important for tasks involving large inputs.
