OpenAI’s stated reason for Codex’s 272k context cap is cache-read cost, not the 2x billing line at the same number
codex ships with a model catalog, and its gpt-5.6 entry lists the context window as 272,000 tokens. the published spec for the model is 1,050,000. 272,000 is also where the api reprices: past that many input tokens the whole request bills at 2x input a…