We definetly need this. Setting the reasoning effort to "high" makes a dramatic difference in output quality.
Red Turtle
•
Jan 27, 2025
From their newsletter…
We're giving you access to OpenAI o1 in the API today. o1, the successor to o1-preview, is our reasoning model designed to handle complex multi-step tasks with advanced accuracy. In the API, it supports function calling, Structured Outputs, vision, and developer messages. We’ve also added a new reasoning_effort parameter, which lets you control how long the model thinks before answering. And compared to o1-preview, it’s lower latency—o1 uses 60% fewer reasoning tokens on average.
Log in to comment and vote
Comments4
Feb 5, 2025
this is now available! https://x.com/TypingMindApp/status/1886429688270332063
Chocolate Pickle
Feb 3, 2025
100% must have, and very easy to implement
Indigo Stew
Jan 30, 2025
We definetly need this. Setting the reasoning effort to "high" makes a dramatic difference in output quality.
Red Turtle
Jan 27, 2025
From their newsletter…
We're giving you access to OpenAI o1 in the API today. o1, the successor to o1-preview, is our reasoning model designed to handle complex multi-step tasks with advanced accuracy. In the API, it supports function calling, Structured Outputs, vision, and developer messages. We’ve also added a new
reasoning_effortparameter, which lets you control how long the model thinks before answering. And compared to o1-preview, it’s lower latency—o1 uses 60% fewer reasoning tokens on average.So it would be good to have.