context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
Why it matters
OpenRouter exposes reasoning traces through include_reasoning, returning them in a reasoning field alongside content. The post demonstrates using one model's reasoning as context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → for a cheaper model, a pattern for splitting thinking from generation.
