The models are beginning to diverge significantly in terms of how many output tokens they will provide. I would like the ability to easily set the max output tokens to the maximum for each model.

I can currently set the max number of tokens for ALL models (the Max Tokens setting in the Manage Models settings) or the max tokens for EACH AI agent. The problem with this is that I do things where I want the max tokens to be set to the maximum allowed by the model. It is very time consuming to switch from one model to another and increase/decrease the max tokens in the applicable settings accordingly.

It would be great if the "Max Tokens" setting for all models (the setting on the Manage Models settings) AND for each AI agent had a setting that would allow the maximum output tokens supported by the chosen model. This way, I can simply change the selected model I'm using (or the AI agent is using) and know that the output I get can be as much as allowed by the model without going into the settings and manually changing it each time.