Rate Limit seems to be global, not per config profile, but many models have different rate limits

[piisawheel]

App Version

3.11.5

API Provider

Google Gemini

Model Used

Gemini 2.0 and 2.5 pro.

Actual vs. Expected Behavior

When I set up different profiles for different llms, I was disappointed to see that the rate limit (under advanced options) was a global value.

This doesn't make any sense, and should be tied to the model configuration profile.
Gemini 2.0 has a (free) rate limit of 15 Requests per minute (1 every 4 seconds), but 2.5 Pro has 5 (was 2) requests per minute. I would like to use different rate limits tied to the profile for the specific model in use. This seems to make a lot more sense than needing to change the global config to accommodate a different model.

[ross]

Looks like #1785 is working to implement this.

[piisawheel]

I apologize then. I did a search for "rate limit" and nothing came up, so I assumed I was the first to complain.