Choice of AI model (Advanced Paste) about powertoys HOT 5 CLOSED

I personally don't mind running my models through OpenAI's APIs, but when offline or for better privacy it would be nice to also specify a locally-running model, such as Llama3, Phi-3, or other SLMs

from powertoys.

I hope to support custom API URLs. I have some Azure APIs converted into OpenAI format.

from powertoys.

3.5-turbo-instruct is what I found in my API usage logs, that is a terrible model to use when one of the 4-turbo models is far superior and we're talking about negligible cost differences when you consider how often someone would use advanced paste

b/c of 3.5 => simple tasks like "convert to c#" doesn't recognize the source language... and so I have to re-prompt with "convert javascript to c#"

please allow us to choose, or at least default to a 4-turbo/4o model

from powertoys.

/dup #32960

from powertoys.

Hi! We've identified this issue as a duplicate of another one that already exists on this Issue Tracker. This specific instance is being closed in favor of tracking the concern over on the referenced thread. Thanks for your report!

from powertoys.