K2Coder can use AI in several ways, including with your own keys or with Quantum Cloud credit. With your own keys, you pay the AI provider directly and none of this applies. With Quantum Cloud credit, you buy prepaid credit from us in US dollars and K2Coder draws on it as it works. This post explains exactly how it draws on it, because a builder that runs for minutes on its own should never leave you guessing what it spent.
Some of the rules below are new. They are built and tested, and they take effect with the next update of the Quantum Cloud service. Each one is marked.
How is each request charged?
Each time K2Coder asks a model for something, two things happen.
Before the request, the most it could cost is set aside. We work out the worst case: the size of what is being sent, plus the longest answer the model is allowed to write, at that model's price. That amount moves from your available credit into a hold. If there is not enough credit, the request stops there and the model is never called.
After the request, you are charged what it actually cost. The provider reports how many tokens it read and wrote; we charge those at the model's price, and the rest of the hold goes straight back to your balance. The charge can never be more than the hold.
Two more rules sit around this:
- Only models with a checked price can be paid for with credit. If we have not confirmed a model's price, it is not offered on credit.
- Claude models are never sold on credit. You can use them through Claude Code, installed on your Mac and signed in to your own Claude plan (K2Coder does not include Claude Code), where your plan's limits and Anthropic's terms apply, or with your own Anthropic API key, billed to you by Anthropic.
A project can have its own budget. When the amount set aside for a request would take a project past its budget, the request is refused before anything is spent.
Can a reply cost more than was set aside? (new)
The hold assumes a longest possible answer. From the next update, the request sent to the model carries that same limit, whichever provider it goes to. A model cannot write a longer answer than the one you were held for.
When is a request settled? (new)
From the next update, a request that runs too long is stopped no later than 4 minutes 40 seconds after it reaches the Quantum Cloud service, and settled immediately, rather than left open, so its cost is recorded straight away.
If a request is cut off after the model already received it, because it ran out of time, the app closed or the answer stream broke, you are charged an estimate of what the model read and what came back before it stopped. The provider charges us for that work either way. If the connection to the provider breaks before it responds, or the request never reached the model at all, nothing is charged.
Can a request be sent, and charged, twice? (new)
Sometimes a provider is busy and turns a request away. From the next update, the Quantum Cloud service only resends a request when the provider has said it did not take it, or when the connection never opened. If there is any chance the model already did the work, the service does not send the same request again. K2Coder itself may start a step again once after a time-out or a server error; that is a new request with its own charge. Either way, you are charged once per request.
What happens to your credit on a refund? (new)
If you ask for a refund on a credit purchase and it is processed, the matching credit comes off your balance. For a partial refund, the matching share. The amount comes from the payment provider's own records, and each refund counts once.
If some of that credit was already spent on builds, the remainder is recorded and your account is paused until it is settled with us. When a card dispute is opened, the disputed credit is taken off your balance and your account is paused until the dispute is resolved with us. We would rather tell you this now than have it come as a surprise.
Where can you see the charges?
Once you are signed in, the Quantum Cloud account card on the Settings page in K2Coder's sidebar shows your balance, any credit reserved for builds still running, and your recent charges. (This is not the Settings window under the K2Coder menu, which holds your provider keys.) After each build, a note in the chat shows what that build cost, and the Build tab shows the project's budget and how much it has spent. Questions about a charge: support@quantumaccordbg.com.