Feature request for product/service
AI Models
Describe the request
I use Auto on Ultra. I don’t pick models by hand. Auto is supposed to be the cost-aware option, and Fast is the same Grok work at twice the token cost. I don’t need that speed for most of what I do. I need the monthly include to last.
Fast is the default in Auto now. There is no setting to leave it off and only enable it when I want the extra speed. Cost, Balance, and Intelligence don’t give me that choice.
Please add a setting to enable Fast for Auto. Account default and per chat, and the same for Cloud Agents and Grok Bot. Off unless I turn it on. Auto can still pick Grok, Composer, or anything else. It should only pick a Fast variant when that setting is enabled.
24 Aug to 2 Sep, on Auto, usage is full of cursor-grok-4.6-high-fast: 6645 events, 617M tokens, 10.5% of the Cursor Models bar, about $1050 at Fast rates. Those same tokens at normal Grok 4.6 rates are about $525. On-demand is zero, so this isn’t a bill. It’s include I don’t get back. The bar is around 20%. If Fast hadn’t been the default, that slice of the bar would have been about half.
Last cycle Fast Grok 4.6 was three events and five dollars. This cycle it’s the biggest named line and I was on Auto the whole time.
If usage listed Auto and the model Auto actually ran, I wouldn’t have needed a CSV to see this.