Feature/Bug Requests

Parasail should document what parameters they support and currently not support, like logit bias, XTC, DRY, etc.

The usage base pricing is great, but I would like a simple way for me to limit my spending, maybe just a simple input of number so can have a peace of mind that I won't burn my wallet without knowning it XD

At the moment not all the serverless models show the context length. It’s helpful to know how much the model can remember.

You don't describe anywhere what you are logging, even though it was said that you log just the "amount" of input and output tokens, what is your policy?

The website is not optimized for mobile view and it could leave a bad impression on the visitor. I suggest you use flexbox to fix the responsiveness. Try visiting the website on your phone.

Download percentage in dedicated when spooling up a model would be greatly appreciated rather than guesstimating its progress.

Currently downloading the model, which is used for inference, can be expensive. For example, downloading Llama 3.3 70B takes over an hour (still running, so it might be multiple hours even). If preparation steps such as this weren't billed, and only the actual compute was, that would be great.

it would be nice on the eyes if the UI had a built-in dark mode toggle :)

When I start an dedicated 70B model, it shows at low cost that it chooses 4x h200s and says "insufficient quota" or something like that. The fix for that is that I have to manually stop the dedicated model and start it again so that it only uses 2x of them, even though I had low cost selected.

I want to click one button that copies the key/model/link, not rip it all out of a python script