OpenAI models may get more reasoning budget through the API than through Codex

Apparently, the same OpenAI models may get way more reasoning budget through the API than through Codex. So even if you’re using OpenAI’s own Codex harness, you could still be getting a more constrained version of the model compared to someone just paying for the API directly. For example, GPT-6 Astra is reportedly around 832 “juice” on Max via API, vs 128 through Codex. (If this is true, and the measurements suggest it might be, then OpenAI is basically holding these models back on its own plans while API users get the real monsters.)