Cursor has gotten more expensive and Claude Code is about to impose new rate limits. To help keep track of your spending and usage I built an open source tracker that tracks both together.

It works in your command line and updates a live dashboard on my website (optional). I also aggregate everyone's token usage together and breakdown the models people are using.

The repo is here https://github.com/ellmanalex/pricepertoken-ai-coding-tracke...

thanks for the feedback!

added

I just added grok

Ouch, bad response for someone with a business!

Unglaublich!

The input is wrong tho

Your website reports 0.30$ for input and that wouldn't make any sense as it would be priced the same as the bigger Flash model.

ok yeah fixed that one, sorry...

such level of condescending behaviour when you yourself are wrong is not allowed.

Put a really really bad taste in my mouth.

First poster could have approach better too. Like "Cool site! I think I may see an error on one item?". Instead of going right to a 'wrong' angle as if all the data should be discredited. I get highly triggered by this too.

this overly positive attitude triggers a bunch of people too. wrong data should just be called out, especially if that's your main selling point.

Nobody disagrees with that. But tact exists.

But why is condescension tolerable when the person is right?

It is not but its order of magnitudes worse if the person is wrong.

would a column for "provider" meaning the place you are actually making the call to solve this

yeah I am going to add an experiment that runs everyday and the cost of that will be a column on the table. It will be something like summarize this article in 200 words and every model gets the same prompt + article

For me, and I suspect a lot of other HN readers, a comparison/benchmark on a coding task would be more useful. Something small enough that you can affordably run it every day across a reasonable range of coding focused models, but non trivial enough to be representative of day to day AI assisted coding.

One other idea - for people spending $20 or $200/month for AI coding tools, a monitoring service that tracks and alerts on detected pricing changes could be something worth paying for. I'd definitely subscribe at $5/month for something like that, and I'd consider paying more, possibly even talking work into paying $20 or $30 per month.

Yeah want to keep it really simple. Appreciate it!

Yeah I am planning on setting up automatic scraping and just having my own database. Maybe could add historical data beyond as well but just gonna save all my own data for now

They all tokenize a little differently so they are not exactly 1-1. However I plan on addressing this by having each model complete a test task and getting the actual price from each api + token count to make a real 1-1 comparison.

And please timestamp the benchmarks, and rerun them periodically, so vendors can't quietly cost optimize the model when no-one's looking.

Ah, that's a great idea and would be a welcome addition to the site.