The maximum amount of text a model can process in a single interaction.
The context window (also called context length) is the maximum number of tokens that a language model can process in a single interaction. This includes both the input prompt and the generated output.
Key considerations:
Context windows range from a few thousand tokens (GPT-3) to hundreds of thousands of tokens (GPT-4 Turbo). When approaching the limit, consider summarizing or truncating less important information.