Toggle Between Fast and Slow Requests

[stoufax]

I would like to request a feature that allows users to toggle between fast and slow request modes. This would help in scenarios where speed optimization or thorough processing is needed, giving users better control over performance and resource usage.

[ziedhajsalah]

+1 agree

[boni]

@stoufax

This would help in scenarios where speed optimization or thorough processing is needed

I’m not sure if I understand this part, slow requests are no different from fast except that you have to wait for them if you’ve ran out of the default 500 fast request credits. Slow requests don’t spend any more time or effort processing your prompt, they just get put in a queue with other users’ requests

[debian3]

Option to Choose Slow vs Fast Requests

As a new user I’m feeling frustration at having used 100/500 fast requests in a matter of the first 3 days of my subscription. I would like the option to choose slow requests during certain sessions when timing isn’t as important. This current model isn’t sustainable for me over the month. And no, I don’t want to buy more fast requests…money matters to me. It seems this would be an easy and popular feature to add. And, yes, I know there are other models to choose from but Sonnet 3.5 is the best …

Toggle Premium Request

I know its been said before in other threads but they are all particular to an LLM model in use and what not. Just in general: Can we please choose whether our prompt is going to be used toward our alotted 500 premium/fast requests or not. AND can we have it presented in a way that is clear and understandable. We dont know which models are free/premium/slow/fast sometimes. We want it to be toggle-able at any time. This kind of already is here, but not really they way we all want it

Option to Toggle Between Fast and Slow GPT-4 Requests

Would be cool if we could get the option to choose to use slow requests. There are times when I want to tweak just a few lines or where speed isn’t important. In these situations, using a fast request feels like overkill, and I often find myself hesitating, wondering if it’s worth consuming one of my limited fast requests. I understand I could use GPT-3, but I don’t really consider it a good alternative to 4 in most situations. Not sure how your backend works, but it might even help with perfor…

How do you change between fast and slow GPT4 requests?

I’d like to be able to use slow GPT for non mission critical tasks and save up my fast requests for when I really need them.

Enable Switching Between Fast and Slow Request Modes for Better Flexibility

I recently upgraded to a Pro subscription, and while I’m working on mapping out my project details, structure, or roadmap, I wanted to switch to slow request mode instead of using up my quota in fast request mode. This way, when I move on to coding tasks, I can switch back to fast request mode and work more efficiently and effectively. However, I couldn’t find such a setting, and unfortunately, my quota is being reduced while I’m having less important conversations. When I reach the most criti…

[ttn]

This feature request has been here since 2023

Cursor will never do it because the slow will be slower due to the increase of number of users on slow side

So stop asking the same question over and over without searching the forum first.

What matters right now is that there should never be slow vs fast to start with. And the 500 limit thing. From user point of view, these stuffs are the least we need to pay attention to, but Cursor is making this a fuss to its users, for their exponential growth revenue, leading to rage quit.

We are all prepared to jump the ship once any AI IDE better than cursor appearing on the market.

This Cursor thing is same like Internet Explorer back then when internet just started. Microsoft lost the browsers market for many many years despite being advantages of OS installations. Now even it has Edge, people still turn their back against them and keep using Google Chrome, due to their painful history time with IE in the past.

I’m interested to see if this history of IE will repeat to Cursor.

[testacode]

I second this, I feel like one of the comments here… 3 days and I’ve already used 120 fast requests with a simple personal project. I can’t picture myself using this for work. Is this product only for devs who get paid over 400k a year?