Glossary
Context window
The maximum amount of text, measured in tokens, that a model can consider at once.
The context window is how much a model can take into account in a single request, including the instructions, any documents provided, the conversation so far, and its own reply. It is measured in tokens.
A larger context window lets a model work with long documents, large codebases, or long conversations without losing earlier material. Companies often advertise their context window size as a selling point.
A model that accepts a very long input does not necessarily use all of it well. Independent tests have found that some models miss or misuse information buried in the middle of long inputs, so the advertised limit is a ceiling, not a guarantee of quality.