Context window

The context window is the maximum amount of text —measured in tokens ✕ A token is the smallest unit of text a language model works with: usually a word or a piece of a word. Pricing and limits are measured in tokens. More in the glossary → — that a language model can take into account at once, including both your instruction and its own response. It works like its working memory: everything that fits inside is considered when generating the answer; whatever spills over is lost. In a long conversation or when pasting a large document, if the limit is exceeded the model starts to "forget" what was said at the beginning, which can lead to incoherent answers. Windows have grown a lot, from a few thousand tokens to hundreds of thousands in the most advanced models, which allows working with entire books or codebases. Knowing this limit helps you structure your requests well and understand why the AI ✕ Artificial intelligence is a computer system’s ability to perform tasks we associate with human intelligence, such as understanding language, recognizing images or making decisions. More in the glossary → sometimes loses the thread.