> For the complete documentation index, see [llms.txt](https://inferra.gitbook.io/inferra-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://inferra.gitbook.io/inferra-docs/inferra-cloud/the-delivery-layer.md). # The delivery layer Delivery is what turns a paid order into a machine you can actually use. When your escrow settles, a slice of the provider's hardware is stood up just for your rental, and you get an SSH command to it. ### What you get Your rental runs in its own isolated environment on the provider's machine, with the GPU passed straight through to you. It is locked down and reachable only with the SSH key you provided. Password and root login are off, so nobody else can touch your slice and you cannot reach anyone else's. You connect the way you would to any remote machine: ``` ssh -p user@ ``` Inside, the card is yours. `nvidia-smi` shows it, and your work runs on real silicon, not a shared queue. ### Metering and cutoff Usage is metered by the GPU-hour against what you bought. You can watch how many of your hours you have used as you go. When the hours run out, or when the 30-day term ends, the slice shuts down on its own and the escrow releases to the provider. You never pay for time you did not use, and there is nothing to remember to tear down. ### Isolation Each rental is its own sandbox: * A dedicated container per rental, with the GPU passed through. * Non-root by default, with system privileges dropped. * Reachable only with your SSH key; password and root login disabled. * Network access restricted to what the workload needs. An on-chain payment maps to time-boxed access to real hardware, not a credit on someone's private ledger. For the funds side, see [The escrow program](/inferra-docs/inferra-cloud/the-escrow-program.md); to list capacity as a provider, see [Becoming a provider](/inferra-docs/inferra-cloud/becoming-a-provider.md). --- # 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 dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://inferra.gitbook.io/inferra-docs/inferra-cloud/the-delivery-layer.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. 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.