Context window
Also: context windows, long context, long-context
How much text the model can hold in mind at once: your question, the documents you added, and the conversation so far. Anything outside it is invisible to the model.
The context window is the size of the desk. Bigger models have bigger desks, but every desk has an edge, and things near the edge get less attention.
The fuller definition
A context window is the amount of information a model can use within an interaction, usually measured in tokens. Instructions, supplied material, conversation, and output compete for capacity under model-specific rules.
Go deeper
2,000
8,000
4,000
2,000
A hypothetical 16,000-token budget. Real limits and token accounting depend on the model. Saving a file outside this budget does not mean it is present in the current context, and a passage inside it is not guaranteed equal attention.
A concrete example
A long transcript can consume space that might otherwise hold earlier conversation or a longer answer.
The distinction that matters
Fitting within a limit does not guarantee complete or equally reliable use of every passage.
Related terms
Token
A piece of text, often part of a word, that the model actually works with. Models read and write tokens, not whole words.
Prompting & contextContext engineering
Choosing what a model gets to work with. Give it the facts and rules it needs. Leave out clutter that may confuse the task.
Prompting & contextCompaction
Squeezing a long conversation into a short summary so there is room to keep going. Details can be lost in the squeeze.
Where it is taught
What actually happens when you ask AI a question?Source and further reading
Google · Machine Learning GlossaryThe definition and example are written for this library. The link gives background, official documentation or legal authority as labelled. Legal scope depends on the jurisdiction and current text; product features depend on release and settings.