> ## 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.

# Quickstart

Claim your provisioned B3IQ node, create a local API key, and make your first OpenAI-compatible local request.

This quickstart gets one provisioned machine to a local OpenAI-compatible chat
request. Your machine arrives with the host agent already installed and set up by
B3IQ. You claim it, create a scoped local key, and call it. Use it when you want
local inference working before you think about earning or hosted gateway access.

**Your machine arrives provisioned**

B3IQ installs and supervises the host agent on the machines it hosts and ships,
  so there is nothing to download or install yourself. The host agent serves the
  local command panel and local inference APIs on `http://127.0.0.1:8831`. Setup
  tokens, owner sessions, and local API keys are powerful local credentials, so
  treat them accordingly.

## Claim the node

**Open the local command panel**

Open the local command panel the host agent serves on your machine. If you
    need a fresh tokenized URL from the machine, run:

    ```bash
    b3iq-host wizard url --with-token
    ```
  **Review inventory**

The wizard reads hardware, OS, runtime, model, and network posture from the
    host agent. Browser GPU checks are advisory only; the host agent is the
    source of truth.
  **Choose mode**

Start with Local Mode unless you are intentionally enrolling the machine
    into managed or network workflows. Enrolling a new machine into managed
    mode needs an onboarding code from the B3IQ team. A machine that has
    already been onboarded instead links to your account by redeeming a claim
    code at [/dashboard/claim](https://b3iq.org/dashboard/claim).
  **Create local owner auth**

Set the local owner account and create a scoped `b3iq_local_` API key for
    local inference clients.
  **Install or select a model**

Pick a model profile the machine can actually serve. Larger network models
    require stronger RAM, VRAM, runtime, and benchmark posture.

## Make a local request

Store keys in files instead of shell history or process argv.

```bash
umask 077
mkdir -p .secrets
# Paste the local key, then press Ctrl-D.
cat > .secrets/b3iq-local-key
```

Call the local OpenAI-compatible chat endpoint. Use a model you actually
installed: list what your node can serve with
`curl http://127.0.0.1:8831/v1/models`. The `model` below is only a placeholder:

```bash
: "${B3IQ_LOCAL_KEY_FILE:=.secrets/b3iq-local-key}"
B3IQ_LOCAL_BASE_URL="${B3IQ_LOCAL_BASE_URL:-http://127.0.0.1:8831}"

cfg="$(mktemp)"
chmod 600 "$cfg"
trap 'rm -f "$cfg"' EXIT
{
  printf 'url = "%s/v1/chat/completions"\n' "${B3IQ_LOCAL_BASE_URL%/}"
  printf 'request = "POST"\n'
  printf 'header = "Authorization: Bearer %s"\n' "$(sed -n '1p' "$B3IQ_LOCAL_KEY_FILE")"
  printf 'header = "Content-Type: application/json"\n'
} > "$cfg"

curl --fail --silent --show-error --config "$cfg" --data-binary @- <<'JSON'
{
  "model": "qwen3-8b",
  "messages": [{ "role": "user", "content": "Run a local B3IQ smoke reply." }],
  "stream": false
}
JSON
```

**Need hosted routing?**

Local keys are not hosted gateway keys. Hosted calls use scoped
  `b3iq_gateway_` credentials and route to the machines on your account. See
  [Hosted Gateway](/developers/hosted-gateway).

## Next steps

**[Host agent](/operators/host-agent)**

The local service behind claiming, runtimes, keys, and local inference.
  **[Model readiness](/operators/model-readiness)**

Learn the full checklist for installed, benchmarked, paid-route-capable profiles.
  **[Local API](/developers/local-api)**

Use local `/v1/models`, `/v1/chat/completions`, model profiles, and receipts.
  **[Route readiness](/operators/route-readiness)**

Understand why a node is or is not eligible for network work.