You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Write an option to support using flex pricing for o3 and o4-mini at OpenAI.
Flex pricing is half the price for input and output tokens at the price of speed of response from the AI or resource unavailable errors during peak usage of the models.
🧐 Proposed Solution
This should be a special feature for these models (o3 and o4-mini and more to come) similar to Effort adjustment in Agent settings. that sets the api option service_tier="flex" in response part of the OpenAI api. It is described https://platform.openai.com/docs/guides/flex-processing in this link
📝 Additional Information
This might cause timeout errors due to timeout delay, can be mitigated by turning on "Client side fetching" for OpenAI platform in platform settings.
The text was updated successfully, but these errors were encountered:
Thank you for raising an issue. We will investigate into the matter and get back to you as soon as possible.
Please make sure you have given us as much context as possible.
非常感谢您提交 issue。我们会尽快调查此事,并尽快回复您。 请确保您已经提供了尽可能多的背景信息。
GitGoppy
changed the title
[Request]
[Request] Add Flex pricing option for o3 and o4-mini OpenAI models
Apr 18, 2025
🥰 Feature Description
Write an option to support using flex pricing for o3 and o4-mini at OpenAI.
Flex pricing is half the price for input and output tokens at the price of speed of response from the AI or resource unavailable errors during peak usage of the models.
🧐 Proposed Solution
This should be a special feature for these models (o3 and o4-mini and more to come) similar to Effort adjustment in Agent settings. that sets the api option service_tier="flex" in response part of the OpenAI api. It is described https://platform.openai.com/docs/guides/flex-processing in this link
📝 Additional Information
This might cause timeout errors due to timeout delay, can be mitigated by turning on "Client side fetching" for OpenAI platform in platform settings.
The text was updated successfully, but these errors were encountered: