It turns out that the official GPT model channels currently running on Codex only have fast/flex left, meaning that if you don't run fast, you get half-price but no guaranteed stability.



No wonder it keeps disconnecting and the first token latency is extremely high—cost reduction and efficiency improvement.
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pinned