传 Codex 里 Astra 推理额度被大幅压缩

Token Gremlin @TokenGremlin原推发布于 2026.09.28

在 X 上打开原推

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.)