The context window is the maximum amount of text – measured in tokens – that a language model can process in a single pass. It includes both input and output. A large context window allows the model to process long documents, entire books, or extensive conversation histories at once. Models with small windows "forget" earlier parts of a conversation. Modern models offer windows from 100,000 to over 1 million tokens.
In short
What is the context window of an AI model?
The context window is the maximum amount of text in tokens that a language model can process in a single pass – input and output combined. A large window allows processing long documents or conversation histories. Modern models offer windows from 100,000 to over 1 million tokens.
Using AI in your organisation?
We show you which applications are worth it for your organisation.