Skip to content

Features

Cost at API rates, per thread

Helicon shows what each Muse Code thread would have cost at Meta's published per token rates, broken down by day, by model and by thread. It is a meter reading rather than an invoice: your subscription already paid, and this is how you find out what it did.

Last updated · Markdown version

What the number means

A subscription hides the thing a per token bill makes obvious: which work was expensive. Helicon multiplies the tokens each turn actually used by the published rate for the model that used them. Nobody charges you this. It is the scale reading, and it is the fastest way to learn which habits are costly.

Three views

  • By thread, so you can see that one refactor cost more than a week of small edits.
  • By day, so a spike is visible before it becomes a pattern.
  • By model, so the difference between reasoning efforts stops being abstract.

What it is not

  • Not a bill. You are on a subscription and Helicon has no billing relationship with you at all.
  • Not an estimate of your plan limit. That is reported separately, as Muse Code reports it.
  • Not sent anywhere. The calculation happens locally against local usage data.

Frequently asked questions

Does Helicon charge me anything?

No. Helicon is free, MIT licensed, with no paid tier. It uses the Muse Code subscription you already have.

Are these numbers exact?

They are token counts reported by Muse Code multiplied by published per token rates. They are exact as an arithmetic exercise and irrelevant as an invoice, because your subscription is what pays.

Can I see usage against my plan limit?

Yes, separately. Helicon shows the 5 hour window and the weekly cap as Muse Code reports them, in the sidebar and on the usage page.

Same Muse Code. Same subscription. Better interface. 

Free and MIT licensed. Signed Windows installer, universal macOS DMG, and a web build against a daemon you run.