Have every model use fast premium requests

So, here’s a new request. Let’s have every model use fast premium requests, each changing based on how much it would cost on the usage based pricing. When the pro subscriber runs out of premium requests, they can then pay more to use the models (either by direct payment like before or by buying request packs) or be limited in which models they can use with the requests slowed down.

Some premium models already charge different amount of premium requests, so why not do it for every model?

Some examples for model pricing if this is implemented:

o1: 10 fast preimum requests per prompt
o3: 7.5 fast premium requests per prompt.
GPT 4.5: 50 fast premium requests per prompt
Sonnet 3.7 MAX and Gemini 2.5 pro MAX: 1.25 requests per prompt and tool call.

And so on.

Similarly, the free requests per day included in pro plan for some models can also be removed.(I doubt anyone is using those models anyways)

I believe this would help reduce the confusion about Cursor’s current pricing model.

1 Like

Since free models (o4-mini and grok-3-mini-beta ) also charges fast credit, I don’t think Cursor will take your advice.

o4-mini isn’t free anymore. And grok-3-mini-beta doesn’t charge fast requests, I just tried it.

At least the document said so: Cursor – Models

If it says free on the price column there, it doesn’t cost anything, not even fast requests. Doesn’t matter if it’s marked premium or not.

Not true for o4-mini…

It doesn’t say free on that anymore either, you might need to reload the page.

Also, here’s the relevant announcement.

One final note: gpt-4o-mini and o4-mini are different models… (the former is free)

Yeah, reload is needed.

up!

1 Like

Weird. Now it appears to be free for me as well.

Edit: Now it seems to be paid again.