Context window
Section titled “Context window”A context window is the bounded amount of tokenized information a language model can process as active context for one inference sequence.
The window can contain instructions, user input, retrieved material, tool results, and generated history.
A larger context window increases capacity, but it does not guarantee that every included detail will be used correctly or efficiently.
Related knowledge
Context engineering for LLM systemsDeliberately select and structure the information a model receives instead of treating the context window as an unbounded memory store.