context window

A context window is the amount of text a language model can take into account at one time: everything in your prompt, plus everything it has produced so far. It is measured in tokens, chunks of text roughly three-quarters of a word each.

A bigger context window lets a model work with whole documents, long transcripts or entire codebases in a single prompt. But size is not the same as perfect recall: models can still overlook information buried in the middle of a very long input, so a large window raises what you can attempt without guaranteeing what you can trust.