> ## Documentation Index > Fetch the complete documentation index at: https://docs.b3iq.org/llms.txt > Use this file to discover all available pages before exploring further. # FAQ Plain answers to the most common B3IQ questions: what it is, local vs hosted, onboarding, runtimes, privacy, earnings, pricing, and pilot status. Short, honest answers to the questions operators and developers ask most. Where something is gated or still in pilot, we say so. **What is B3IQ?** B3IQ is a neocloud: dedicated GPU machines, bought through B3IQ or enrolled from your own hardware, that serve **your** inference with no per-request charge through an OpenAI-compatible gateway. The host agent gives a machine a node identity, local OpenAI-compatible endpoints, runtime and benchmark probing, signed heartbeats, and receipts, and the control plane binds it to your account so your own API keys and CLI can reach it. Earning is optional, and it is a property of the machine's hosting arrangement rather than of the requests it serves: B3IQ sells the machine's capacity by the hour, and the machine's share of that accrues to its deal ledger. **[Local and managed use](/concepts/local-managed-network)** How the three operating modes fit together. **Local vs hosted: what's the difference?** The **local API** runs on your own machine. The host agent serves an OpenAI-compatible endpoint at `http://127.0.0.1:8831`, backed by whatever runtime and model you have installed. No routing, no billing. Your prompts and outputs stay local unless you send them to a routed workflow. The **hosted gateway** at `https://b3iq.org/v1/api` is a network endpoint. It routes your requests across the machines on **your own account** by health and readiness, enforces customer policy, and meters usage. Inference is free. You call it like any OpenAI-compatible API with a gateway key. **[Local API](/developers/local-api)** Use the host agent as a local endpoint. **[Hosted gateway](/developers/hosted-gateway)** Route across the machines on your account. **Do I have to be approved to run a node?** There's no approval step. Joining the fleet is invite/manual onboarding: a new machine enrolls with an onboarding code the B3IQ team issues, and a machine that was pre-onboarded on your behalf is linked to your account by redeeming a claim code in the dashboard. Once a machine is onboarded and claimed, it can serve your own inference when its connection, runtime, installed model and key scope are ready. Claiming alone does not establish readiness or earnings. Optional earning availability and mode changes are arranged with the B3IQ team under your hosting agreement. **[Operator onboarding](/protocol/operator-approval)** How a machine joins the fleet: onboarding codes, claim codes, and route readiness. **Which runtimes are supported?** B3IQ installs and supervises Ollama, llama.cpp, LocalAI, and Xinference, and it can also point at a runtime you provisioned yourself as long as it speaks an OpenAI-compatible API (vLLM, SGLang, TensorRT-LLM, and others). Machines run Linux. The setup wizard probes the machine and recommends a runtime; the host agent verifies it is reachable before a model profile is marked route-ready. **[Runtimes](/operators/runtimes)** Which runtime a given machine should use, and how installs are verified. **Can I manage my machines from the terminal, or SSH in?** Yes. The `b3iq` CLI signs in with `b3iq login` (a browser device flow) or a personal access token from Settings → CLI tokens, then lets you list machines, install or remove models, restart runtimes, tail logs, and open an SSH session, all without touching a `ProxyCommand`. Each machine also has a native SSH lane you can enable from its dashboard page, and organizations can set fleet-wide SSH keys that reconcile onto every machine they own. **[CLI commands](/operations/cli-commands)** Install, sign in, and the full `b3iq` command set. **Is my data private?** Transport is encrypted from public surfaces and between nodes and the control plane, and the control plane does not retain the prompts or outputs of routed gateway requests. But be clear-eyed about the trust boundary: when work runs on a node, the **node operator can see the plaintext** prompt and output for that request, because inference happens in process on their machine. Verified-confidential / TEE execution (where the operator could not read request content) is **future work**, not something B3IQ provides today. Do not treat routed inference as confidential against the node operator. **[Privacy boundary](/protocol/privacy)** The active transport boundary and the future confidential-compute path. **How do I earn / get paid?** Earn is optional: B3IQ offers eligible whole-machine capacity to external GPU marketplaces by the hour. Income accrues only when capacity is rented; demand is not guaranteed. Under Managed Hosting, the owner receives 85% of gross rental revenue before hosting costs. Earnings are denominated in USD; settlement follows the agreed terms. Estimates, accrued revenue and paid funds are separate records. In **Earn mode**, the machine is unavailable to your B3IQ inference API and SSH. Arrange changes with our team after running work finishes. In **Bare metal**, your account's API keys use your own machines free of per-request charges; serving those requests creates no earnings. Installing a model or passing route-readiness checks does not create rental income. **[Claiming and earnings](/operators/earnings)** Claim a node and read earnings plus payout history. **[Route readiness](/operators/route-readiness)** Why a node is eligible or blocked for routing. **What does the hosted gateway cost?** Inference is **free**. Buy (or bring) a machine, claim it to your account, and your API keys route to it at no per-request charge: there are no credits, no prepaid balance, and no top-ups. Usage is metered per key and per account so you can see what ran, and accounts carry an optional daily token quota that defaults to uncapped. Serving your own requests is not what pays you — a request is metered and receipted, but the machine **earns** on the capacity B3IQ sells by the hour under your hosting arrangement. See the earnings page. **[Usage & quotas](/developers/usage-and-quotas)** Free inference, metering, rate limits, and the token quota. **[Claiming and earnings](/operators/earnings)** What a machine earns on, and how payouts reach you. **How do I get help or report a problem?** Open a ticket from the dashboard's Support tab. Replies from the B3IQ team land on the same thread. B3IQ also emails a machine's owner automatically if it goes offline, its GPU runs hot, or its disk fills up, so you don't have to watch the dashboard for early warning signs. **How do I confirm readiness for my deployment?** Check the dated release and acceptance evidence for the intended machine, model and support scope. Source capability, a historical pilot, a merged change and a deployed release are different states. Verify discovery and a small request with the key your application will use. **[Current status](/operations/current-status)** Current service boundaries, historical evidence and release acceptance. ## More **[Introduction](/introduction)** What B3IQ is and how the pieces fit together. **[Glossary](/reference/glossary)** Definitions for nodes, receipts, route tiers, and more. **[Host agent](/operators/host-agent)** The local service behind every node. **[API overview](/developers/api-overview)** OpenAI-compatible endpoints and gateway basics.