> For the complete documentation index, see [llms.txt](https://docs.podtorrent.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.podtorrent.com/concepts/receipts-and-billing.md). # Receipts and billing Every request is metered, and both sides sign what they saw. Money only moves for requests where both sides agree. ## What a request costs The serving node's price, for the request's tier: ``` cost = (input tokens − cached tokens) × input price + cached tokens × cached input price + output tokens × output price ``` Prices are per million tokens, in US dollars. Token counts come from the engine's `usage`. ## Signed receipts After each request: 1. The node sends a **receipt**: request id, model, status and token counts, signed with a key it made at start. 2. The network compares it with its own reading of the same response. 3. The network replies with its own signed receipt, adding the tier and the cost. If both receipts agree, the request is **matched** and the operator is paid for it. If they differ, or the node sent none, it's recorded but not paid. Receipts hold counts only, never prompts or answers. The network's public signing key is published at `GET https://api.podtorrent.com/v0/network/keys`, so operators can check the network's receipts themselves. ## What receipts prove, and what they don't They prove both sides saw the same token counts. They don't prove the counts are right, or that the node ran the model it claims. Checks for that, using test requests, are planned but not built yet. ## Agent versions Receipts need agent v0.2.0 or newer. Older agents still serve requests, but their work is never matched, so it isn't paid. {% hint style="info" %} Automatic payouts to operators aren't built yet. Matched requests are recorded so earnings can be settled. {% endhint %} --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.podtorrent.com/concepts/receipts-and-billing.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.