Support OpenAI service_tier Parameter
Jason Pratt
OpenAI o3 and o4-mini support Flex processing: this feature provides significantly lower costs for Chat Completions or Responses requests in exchange for slower response times and occasional resource unavailability.
To take advantage of Flex processing, you have to set the "service_tier" parameter to "flex" in your API request (Chat or Responses).
Cagri Yucel
This is now getting expanded to other models.
https://openai.com/api-priority-processing/
An example of the implementation can be seen in Roo Code settings. Would be great to have the same in BoltAI.
Jason Pratt
GPT-5 now supports service_tier as well.