System instructions, conversation history, retrieved documents, tool results, and output all consume this capacity according to the API's accounting. Applications manage the limit through selection, summarization, truncation, or external memory.
A context window is the bounded set of input and generated tokens a model can consider in one interaction.
System instructions, conversation history, retrieved documents, tool results, and output all consume this capacity according to the API's accounting. Applications manage the limit through selection, summarization, truncation, or external memory.