Reduce flow-credit usage by automatically using Cascade Base to run tools that pull in context | Voters

Reduce flow-credit usage by automatically using Cascade Base to run tools that pull in context

Bala Bosch

Using a model like Claude 3.7 Sonnet usese a lot of flow credits on tasks (like pulling in context) that can much cheaper be done using free models like Cascade Base or Deepseek V3 (once its tool usage gets better)
Build in a feature to allow-list certain types of tool calls to automatically use Cascade Base instead of the selected, expensive, model.
This would vastly reduce flow credit consumption by models like Claude 3.7 Sonnet

March 17, 2025

Antoine

I've spent 150$ this weekend. This is unsustainable. At this point copy pasting manually the errors into cursor doesn't sound too bad. I'm switching next month if this is not fixed.

Jeremy Schoemaker

Antoinehi

Marvin

100% this must be solved.. My usage remains relatively constant and I was  always getting over the month with my paid plan, but after an update in the last few weeks, credit usage has been skyrocketing that I had to purchase additional credits after just one week.
I simply stopped paying and I advise anyone else here to do the same until this stops. US Companies only understand money...
Update: 
I looked into viable alternatives and after some try and error, for now, Cline / Roo Code with OpenRouter seems to be the next best alternative. Given how long this issue lingers around without being addressed,  I suspect selling flex credits is their actual business model with the implication that the problem will never be resolved. Asking for better pricing is a bit like asking Tesla to make trucks that aren't glued together and fall apart. Yes you can ask, but nobody will change anything because that's how they make money.

Paulo Vargatt

That's right, before (2 months ago) windsurf, didn't use so many flow credits because the model read the file only once, now it reads 200 lines at a time, making the flow credits be used much faster, it didn't happen before! now we have a situation where we use half of the prompt credits (250) for 1500 flow action credits executions.

Mike Thomas

I don't understand why cascade reads 100 lines of code one time and then 20 lines of code the next. I burn through so many credits just reading code. Ridiculous.

Matej Mulej

Just got an email that such feedbacks exist and can be voted on. Seeing this one makes me hope more people will click on the link, because it's a supreme suggestion. I too had to make a rebuy to continue playing last month. And I don't consider myself in the top percents of heavy users at all. How can this have only 29 votes?

Yassine Boumiza

Smart +1000 to this one as I may consider Cursor if my current can't keep up with my requests (40% new features / 60% debugging & deploying fixes)

Kevin Wessa

100% the best suggestion I've ever seen, and likely can "solve" a lot of user frustrations surrounding credit usage.

Cody Frisch

The only issue I see is that its likely Claude that is requesting to read in the file for example. So its not like Cascade Base can take over reading it into Claude's cache.

Symbion

Very good idea! +1

Luke Sidney

The absolute best feedback suggestion on here. bump this up they need to see this! now models are pulling context, using memory, using MCP, solving lint errors, especially if you're coding typescript you're cooked... i used 250 credit in one day with 48 prompts. at this rate ill have to buy 10$ credit packs every 7 days & it makes no sense. we need 2000 credits on the pro plan and tweak these models so they run less excessive loops in case they are not providing the correct answer.

→