Zero markup. Zero black boxes.

You pay each provider their exact list price. We add $0 per token — the platform is funded by plans, not by a spread on your traffic.

No blended rate, no rounded-up token count, and no “our price” column sitting next to theirs.
Cached and repeated prompt tokens bill at the provider’s cache rate across 5-minute and 1-hour windows.
cached_tokens and the provider’s own unit price appear on every receipt.

The provider’s price. Full stop.

No blended rate. No rounded-up token count. No column labelled “our price” sitting next to theirs. We add exactly $0.00 per token, on every plan including the free one, because the platform is paid for by subscriptions rather than by a spread on your traffic.

A receipt, not an estimate.

Each request shows the grade, the model that served it, the provider behind it, the unit price they charge and the tokens that came from cache. Cost stops being a number you reconcile at month end and becomes something you can read one call at a time.