Massive Slowdown with Gemini-2.5-pro-exp-03-25 — Anyone Else?

Since the release of the new Gemini 05-06 model just a few days ago, I’ve noticed a dramatic slowdown in the Gemini-2.5-pro-exp-03-25 model when running in the slow queue. This used to be my go-to because of its near-instant responses, but now it often takes 30 seconds to 2 minutes to reply.

The Flash model still responds quickly, but the quality feels noticeably worse—it struggles with complex tasks and image handling. Auto Mode hasn’t been much help either since it doesn’t show which model is active, and the response quality has been underwhelming.

Is anyone else seeing this? Could it be rate-limiting from Cursor or Google? Or is it just a traffic spike from users flocking to test the new model? I haven’t found any official updates yet, so I’m hoping it’s a temporary hiccup.

Would love to hear if others are experiencing this—and if you’ve found any workarounds.

9 Likes

Yes , me too. So I unsubscripted

3 Likes

Yes. Me too. Previously it still responded quite quickly even if it was a slow request. But now it is probably long as Claude 3.7 Sonnet in a slow request.

rate-limiting from Google and new free-tier china students))))

same here. I just tested it and it’s 1 minutes 30 seconds wait time on average.

It was never like this until two days ago. It was 5-10 seconds wait time tops.

And I don’t believe it’s the load balance issue but hard-imposed wait time.

It feels like eternity.

1 Like

Same here…
Insanely slow since yesterday.. I don’t know why :frowning:

Massive slowdown across all models. I’m literally trying to do now with agent, choosing any models (i’m on paid subscription) it’s ‘generating …’ endlessly
After like 15 minutes i get message that “Your conversation is too long. Please try creating a new conversation or shortening your messages.”
The conversation is not too long… maybe 4-5 back and forth

Yep, since yesterday, pretty much unusable.

2 Likes

That’s a good point. Could it be all of the students now using cursor?

I think I might jump ship.

Probably they included the model into our “Fast Requests” limit, previously this wasn’t a feature before. Cursor is being greedy.

Yesterday and today i got pretty slow responses compared to the weeks before from gemini-2.5-pro-03-25, but wow it’s now outputting like 3 times more text and analysis when i ask it to review something on my codebase. I think the wait is worth it on this new updated model! I heard the gemini-2.5-pro-03-25 is now actually rerouting to gemini-2.5-pro-05-06 since a few days right? So, yeah, very different from before, big waiting time now on par with 3.7 sonnet, but the output quality and the fact it does go very deep into the “last mile” of the code analysis when it needs to is pretty impressive. I hope this new behavior on Gemini 2.5 pro will last!
For quick responses, i guess i’ll just switch to GPT4.1, it’s good enough for most simple to medium complexity requests.

1 Like

super slow !!!

It seems like we’re back again now!! Only taking between 5-10 seconds now to respond which is awesome!!

According to openrouter :

Not sure if Cursor uses OpenRouter under the hood… if it does, it makes sense..

Yes, I can confirm. If it’s the Cursor team who made the change, kudos to them!

1 Like