# Full P-Node quickstart

Source: https://nodedocs.mor.org/providers/full/quickstart

This page covers a **non-TEE provider** running on your own infrastructure. For TEE-hardened deployment on SecretVM, see [SecretVM quickstart](/providers/full/secretvm-quickstart). Hosted alternatives: [Docker](/providers/full/proxy-router-docker), [AWS EC2](/providers/full/aws), or [Akash](/providers/full/proxy-router-akash).

## Assumptions

- Your AI model is configured, started, and reachable from the proxy-router host on a private endpoint (e.g. `http://my-model.example:8080`). For testing, a local `llama.cpp` server with `tinyllama` works fine — adjust `models-config.json` if your local port differs.
- You have a funded wallet on BASE (MOR + ETH) and the **private key** for `.env`.
- You have your **own** ETH node URL — Alchemy or Infura private API key for BASE works (`wss://base-mainnet.g.alchemy.com/v2/<key>` or HTTPS). The proxy-router has a built-in round-robin of public RPC endpoints as a fallback, but it is rate-limited and unreliable in practice; running a real provider on it leads to silent missed events. Set `ETH_NODE_ADDRESS` explicitly.
- Your proxy-router has a **publicly accessible endpoint** for the provider (`host:port`, no protocol), e.g. `mycoolmornode.example:3333`.

## Install & configure

<Steps>
  <Step title="Get the software">
    <Tabs>
      <Tab title="Release binary">
        The proxy-router ships as a **standalone binary**. Download the **latest** one for your platform from [Releases](https://github.com/MorpheusAIs/Morpheus-Lumerin-Node/releases). Mainnet builds have no suffix; testnet builds end in `-test`. Asset names look like (version will differ):

        | Platform | File |
        |----------|------|
        | Linux (x64) | `linux-x86_64-morpheus-router-<version>` |
        | Linux (ARM64/Raspberry Pi) | `linux-arm64-morpheus-router-<version>` |
        | macOS (Apple Silicon) | `mac-arm64-morpheus-router-<version>` |
        | macOS (Intel) | `mac-x64-morpheus-router-<version>` |
        | Windows (x64) | `win-x64-morpheus-router-<version>.exe` |
      </Tab>
      <Tab title="From source">
        ```bash
        git clone -b main https://github.com/MorpheusAIs/Morpheus-Lumerin-Node.git
        cd Morpheus-Lumerin-Node/proxy-router
        ./build.sh
        ```
      </Tab>
    </Tabs>
  </Step>
  <Step title="Create a working directory">
    The proxy-router reads its config (`.env`, `models-config.json`) and writes its state (`./data/`, `.cookie`, `proxy.conf`) relative to the directory it runs from, so give it a dedicated one and move the binary there (adjust the filename to the version you downloaded):
    <Tabs>
      <Tab title="macOS">
        ```bash
        mkdir -p ~/morpheus-router && cd ~/morpheus-router
        mv ~/Downloads/mac-arm64-morpheus-router-* ./proxy-router
        chmod 755 proxy-router
        xattr -c proxy-router   # clear the quarantine flag (build is not notarized)
        ```
      </Tab>
      <Tab title="Linux">
        ```bash
        mkdir -p ~/morpheus-router && cd ~/morpheus-router
        mv ~/Downloads/linux-x86_64-morpheus-router-* ./proxy-router
        chmod 755 proxy-router
        ```
      </Tab>
      <Tab title="Windows">
        Create `%USERPROFILE%\morpheus-router`, move the downloaded `win-x64-morpheus-router-<version>.exe` into it, and rename it to `proxy-router.exe`.
      </Tab>
    </Tabs>
  </Step>
  <Step title="Create .env">
    In the working directory, create a `.env` file. Start from the repo's [`proxy-router/.env.example`](https://github.com/MorpheusAIs/Morpheus-Lumerin-Node/blob/main/proxy-router/.env.example) (`.env.example.win` on Windows) — the standalone binary does not ship one. Edit at minimum:
    - `WALLET_PRIVATE_KEY=` — provider's private key.
    - `ETH_NODE_ADDRESS=` — **required for any real deployment.** The minimal example file does not set this; without it the node falls back to a built-in public RPC round-robin that is rate-limited and unreliable. Use your own Alchemy / Infura HTTPS or WSS URL. Match `ETH_NODE_USE_SUBSCRIPTIONS` accordingly (`true` for WSS, `false` for HTTPS — recommended HTTPS + `false`).
    - Choose **mainnet** (default) or testnet — uncomment the testnet block, comment mainnet, save.

    Full reference: [Env: proxy-router](/reference/env-proxy-router) (see "Conflicting / overlapping variables" up top).
  </Step>
  <Step title="(Optional) external / pass-through providers">
    To resell or front another LLM, create `models-config.json` in the working directory, set `MODELS_CONFIG_PATH=./models-config.json` in `.env`, and add the entry:
    ```json
    {
      "modelId": "<your_modelId_from_chain>",
      "modelName": "your-model-name",
      "apiType": "openai",
      "apiUrl": "https://api.example.com/v1/chat/completions",
      "apiKey": "..."
    }
    ```
    Full schema: [models-config.json](/reference/models-config). Restart after edits.
  </Step>
  <Step title="(Optional) provider weights & allowlist">
    Create `rating-config.json` in the working directory (and set `RATING_CONFIG_PATH=./rating-config.json` in `.env`) to bias selection or restrict to specific providers:
    ```json
    {
      "algorithm": "default",
      "providerAllowlist": [],
      "params": {
        "weights": { "tps": 0.24, "ttft": 0.08, "duration": 0.24, "success": 0.32, "stake": 0.12 }
      }
    }
    ```
    Weights must sum to 1. Reference: [rating-config.json](/reference/rating-config).
  </Step>
</Steps>

## Start

Run from the working directory (so the relative config and data paths resolve):

<Tabs>
  <Tab title="macOS / Linux">
    ```bash
    cd ~/morpheus-router
    ./proxy-router
    ```
  </Tab>
  <Tab title="Windows">
    Double-click `proxy-router.exe` in `%USERPROFILE%\morpheus-router`. Allow Defender if prompted.
  </Tab>
</Tabs>

## Validate

- `http://localhost:8082/swagger/index.html` should render.
- `./data/` directory contains logs.
- The proxy-router log should include:
  ```
  INFO  proxy state: running
  INFO  HTTP  http server is listening: 0.0.0.0:8082
  INFO  TCP   tcp server is listening: 0.0.0.0:3333
  ```

## Next: register on chain

Once running:

1. Look up existing models on [active.mor.org/status](https://active.mor.org/status) — prefer bidding on an existing `modelId`.
2. Register via [MyProvider](/providers/full/myprovider-gui) if your admin API is reachable over HTTPS (or use the desktop/local app for HTTP `:8082`); otherwise use Swagger. Full steps: [Register on chain](/providers/full/register-onchain).
3. Run the [self-checks in Verify your provider setup](/providers/full/verify-setup) before declaring victory.

Mint a new model only when nothing suitable exists (or you need a new `tee`-tagged listing).

## What can cost you MOR during setup

A few things will quietly draw down your MOR balance during initial configuration. None of them are slashing or forfeiture; they are normal protocol fees and stakes. Knowing them upfront prevents the "I lost ~2 MOR during setup, what happened?" support ticket.

| Event | Cost | Refundable? |
|-------|------|-------------|
| Register provider (`providerRegister`) | `0.2 MOR` (or `10000 MOR` for subnet) | **Yes**, on `providerDeregister` (after deregistration cooldown opens) |
| Register model (`modelRegister`) | `0.1 MOR` | **Yes**, on `modelDeregister` (model must have no active bids) |
| **Post a bid** (`postModelBid`) | **`0.3 MOR` non-refundable `marketplaceBidFee`** | **No** — every bid post charges this fee |
| BASE gas | a few cents in ETH-on-BASE per tx | No (standard gas) |
| Sessions consumed before your node was actually serving | Possibly small — see "Disputed early closes" in [Sessions: stake, close, claim](/concepts/sessions-stake-close-recover) | n/a |

The most common pattern: a new provider posts a bid, tweaks their setup, **deletes and reposts the bid** several times. Each repost charges `0.3 MOR`. Six iterations is `~1.8 MOR` gone before the node is even serving traffic.

**Mitigation:** finish your model and `models-config.json` setup, run [verify-setup steps 1-4](/providers/full/verify-setup) **before** posting your first bid. Repost only when pricing actually needs to change.

For details on bid pricing and how to change a price, see [Pricing](/providers/full/pricing).