> 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/overview.md). # Overview Inferra Cloud is a marketplace for GPU compute. Providers list real machines, renters pay in USDC and get SSH access, and the payment waits in an on-chain escrow that reaches the provider only after the machine is delivered. No one holds anyone else's money along the way. ### How it works You choose a GPU model and a provider, and you rent capacity by the hour. Your payment goes into escrow, tied to that one order. When the machine is handed to you over SSH, the provider is paid and the escrow closes. If the machine never arrives, you are refunded. You sign the transaction yourself, so your funds are never in anyone else's custody, and a provider is never paid for compute they did not deliver. Rentals are priced in dollars and settled in USDC, so a rate means what it says. ### What you can rent Inferra Cloud lists six GPU tiers. The A5000 is available to rent directly; the rest are onboarded on request as providers bring capacity online.
TierCardBest for
A5000RTX A5000, 24GBInference and development
A10080GB SXMReliable training workhorse
H100SXM, NVLinkTraining and fine-tuning
H200141GB SXMLong-context training
MI300X192GBAMD alternative
B200Blackwell, 180GBFrontier training
Capacity spans several regions, including us-east, us-west, eu-west, eu-north, and ap-south. ### The language of the marketplace Inferra Cloud talks about renting, not trading. You rent capacity at a rate and take delivery of a machine. The rate follows the live [GPU-hour index](/inferra-docs/the-ecosystem/the-gpu-hour-index.md), so you always pay a real market price. If you want to trade that price rather than rent against it, that happens on the [Inferra terminal](/inferra-docs/inferra-terminal/overview.md). ### Where to go next * [Renting compute](/inferra-docs/inferra-cloud/renting-compute.md): the renter's flow, from picking a model to an SSH command. * [Becoming a provider](/inferra-docs/inferra-cloud/becoming-a-provider.md): how operators list capacity and get paid. * [The delivery layer](/inferra-docs/inferra-cloud/the-delivery-layer.md): how a paid order becomes a running machine. * [The escrow program](/inferra-docs/inferra-cloud/the-escrow-program.md): the on-chain program that holds the funds. --- # 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/overview.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.