Nice idea. Can I choose a strategy for token reduction, based on what I'm optimzing for? I might be ok with a quality drop for a great cost savings, for example.

Yeah, you can set roughly the target ratio through the api (for example, target_ratio=.3), though our api will try to maximize the quality given the this target ratio (and it might add a couple more tokens to do so)

why is the landing page straight up taken from wisprflow?

Fair criticism. I replaced that borrowed hero treatment and redeployed the homepage with a native Rose/Adola hero today. It was a bad first impression for a technical audience, especially for something asking people to trust an API in their LLM pipeline.

Thank you so much for your information

I like it thanks a lot

I LIKE IT thanks a lot

Really impressive work. The code is clean, well-structured, and easy to follow. Thanks for sharing this with the community!

Impressive work, thank you for sharing the code. Keep it up!

whoa thanks for this code <3

Hi good evening.

this really worked much than i expected

Eu gostei bastante e estou muito satisfeita

Gostei muito.

It honestly looks amazing to me

Thanks for the code It's amazing and useful

Impressive work, thank you for sharing the code. Keep it up!

Wonderful information Your code this really worked

thi code is very easy to follow , keep it up. im lucky to see it

Woah thanks for the code!! Really appreciate it

I truly appreciate the work put in the code. Great Work.

Thanks for sharing this. The code looks clean and well organized.

Amazing work — clean, smooth, and very professional code

Amazing work on this code! Everything is clean, organized, and easy to understand.

Great for the support. Thanks a lot

thank you so much for this. you're a savior

"Thanks for sharing this, the code looks really clean."

what a graet code

good job keep going

thanks for this code <3

I like it thanks a lot

The work is good and amazing and i like it and so organized!

The comments here are botted.