> ## Documentation Index
> Fetch the complete documentation index at: https://docs.fortytwo.network/llms.txt
> Use this file to discover all available pages before exploring further.

# FAQ

## MCP

<AccordionGroup>
  <Accordion title="What is Fortytwo MCP?">
    Fortytwo MCP is an orchestration layer that allows any MCP-compatible client to access Fortytwo Network directly.

    It implements the [Model Context Protocol <Icon icon="arrow-up-right" />](https://modelcontextprotocol.io/) — a standard that exposes available tools to applications, AI models, and agents enabling them to interact with external services.
  </Accordion>

  <Accordion title="Can MCP be used with my app or agent to access Fortytwo?">
    Yes. MCP is a protocol that exposes Fortytwo tools to applications, models, or agents so that they can easily access Fortytwo.
  </Accordion>

  <Accordion title="Can I use Fortytwo MCP without an API key?">
    Yes. MCP works without an API key. Instead, [x402Escrow <Icon icon="arrow-up-right" />](https://www.platform.fortytwo.network/x402escrow) protocol will serve as your authorization and payment method by utilizing your web3 wallet.
  </Accordion>

  <Accordion title="What is x402Escrow used for?">
    x402Escrow enables low-cost payments for AI inference while allowing the user to remain in control of their wallet and expenses.

    x402Escrow is a special variation of x402 protocol that is designed by Fortytwo specifically to enable usage-based, pay-per-token billing for AI services, charging only for the tokens used. It works in two steps:

    1. Estimated USDC amount is reserved in an escrow contract.
    2. Inference result is provided to the user, the amount for that result is charged, and the remaining funds are released back to the user.

    The key difference between x402 and x402Escrow:

    * x402 protocol relies on fixed price endpoints where costs are known before the operation.
    * x402Escrow is specifically built to handle AI inference usage cases, where the costs are unknown at request time and only become known when inference is completed.

    Learn more:

    * [What is x402Escrow <Icon icon="arrow-up-right" />](https://www.platform.fortytwo.network/x402escrow)
    * [Open-sourced GitHub <Icon icon="github" />](https://github.com/Fortytwo-Network/fortytwo-x402Escrow)
  </Accordion>

  <Accordion title="How much USDC do I need?">
    x402Escrow requires at least 2 USDC on Base or Monad networks. This should be enough to cover multiple requests within a session.
  </Accordion>

  <Accordion title="Which payment networks are supported?">
    USDC payments are accepted on:

    * **Base**: `eip155:8453`
    * **Monad**: `eip155:143`
  </Accordion>

  <Accordion title="What’s the official x402Escrow contract address (CA)?">
    The contract is deployed on Monad and Base networks:<br />
    Monad: [0x9562f50f73d8eE22276F13A18D051456d8D137a0 <Icon icon="arrow-up-right" />](https://monadscan.com/address/0x9562f50f73d8eE22276F13A18D051456d8D137a0)<br />
    Base: [0x9562f50f73d8eE22276F13A18D051456d8D137a0 <Icon icon="arrow-up-right" />](https://basescan.org/address/0x9562f50f73d8eE22276F13A18D051456d8D137a0)
  </Accordion>

  <Accordion title="What happens when my session expires?">
    The server responds with `410 Gone` or `402 Payment Required`. Sign a new payment and start a new session. See [MCP Integration -> Step 5](/docs/mcp-integration#step-5-session-expiry-and-re-payment) for details.
  </Accordion>

  <Accordion title="What if the fund release does not happen?">
    A fallback refund is available on-chain via `refundAfterTimeout(escrowId)` after the escrow's `refundAt` deadline (\~90 minutes). See [MCP Integration -> Fund Release](/docs/mcp-integration#fund-release) for details, or contact [support](https://discord.com/invite/fortytwo).
  </Accordion>
</AccordionGroup>

## API

<AccordionGroup>
  <Accordion title="How do I get API access?">
    Submit an [application form to get API Access <Icon icon="arrow-up-right" />](https://tally.so/r/mYNDW5).
  </Accordion>

  <Accordion title="Can I integrate Fortytwo API with third-party chat Apps?">
    Yes. Read '[Integration with Chat Apps](/docs/api-integration-chat-apps)' to learn how.<br />
    This page currently covers [Jan <Icon icon="arrow-up-right" />](https://www.jan.ai/) and will be expanded with other apps over time.
  </Accordion>
</AccordionGroup>

## P2P Network

<AccordionGroup>
  <Accordion title="What’s the official FOR contract address (CA)?">
    For devnet: [0xf6B888f442277F01294F94D555608A2E8Bc86430 <Icon icon="arrow-up-right" />](https://testnet.monadexplorer.com/token/0xf6B888f442277F01294F94D555608A2E8Bc86430)
  </Accordion>

  <Accordion title="How can I see the amount of FOR I have in my third-party wallet?">
    To be able to see the **FOR** devnet token, you'll need a wallet that allows **importing custom tokens**, like [MetaMask <Icon icon="arrow-up-right" />](https://metamask.io/).

    1. In your wallet, choose option **Import Tokens**.
    2. Select a network: **Monad Testnet**.
    3. Define the token contract address: **0xf6B888f442277F01294F94D555608A2E8Bc86430**
    4. Give it a name: **FOR(DEVNET)**

    After this, it should appear in your wallet. You might be required to select the Monad Testnet network as a category first. <b>FOR(DEVNET)</b> token that you just added will appear in this network's list.
  </Accordion>
</AccordionGroup>

## P2P Inference Nodes

### Devnet Program

<AccordionGroup>
  <Accordion title="How do I join the Devnet program and get an activation code?">
    To receive an activation code, fill out our participation form at [https://tally.so/r/wQzVQk <Icon icon="arrow-up-right" />](https://tally.so/r/wQzVQk). You will receive a single-use activation code in an e-mail.
    See the '[Participate in the Devnet Program](/docs/participation)' page for details.
  </Accordion>

  <Accordion title="Can I run a node without an activation code?">
    Yes. Just follow this '[Quick Start](/docs/quick-start)' guide. With no activation code, you’ll need to manually monitor and top-up MON and FOR balance for your node to work, with 2 MON and 100 FOR required to start a node. Your node will not automatically receive MON refills with no activation code.
  </Accordion>

  <Accordion title="Can I use the same activation code for more than one node?">
    No. Activation codes are one-time use only.
  </Accordion>

  <Accordion title="Can I transfer MON out of my node's wallet?">
    It depends on how you participate in the network:

    <CardGroup>
      <Card title="Case A: Your node receives automated gas compensation for participation.">
        ***

        **Do not transfer MON out of your wallet** in this case. This will terminate the compensation cycle on your node and you will have to fund your participation by yourself. You will not be able to return to the compensation program again.
        Your participation in the Devnet program will continue as usual as long as there is enough MON to pay for gas.
      </Card>

      <Card title="Case B: You cover your node's gas consumption manually.">
        ***

        You are free to **refill and transfer MON out of your wallet as needed.**
      </Card>
    </CardGroup>

    You can read more on '[Holding MON in Your Wallet](/docs/holding-MON)' page.
  </Accordion>

  <Accordion title="My MON balance hit zero and hasn't refilled, what now?">
    If you used an activation code, your wallet is usually refilled within 24 hours. If it’s been longer, message us on [<Icon icon="discord" /> Discord <Icon icon="arrow-up-right" />](https://discord.gg/fortytwo). Reminder: auto-refill works only for wallets tied to activation codes.
  </Accordion>

  <Accordion title="How can I get more MON for my node?">
    You can get MON testnet tokens via the official [Monad's Faucet <Icon icon="arrow-up-right" />](https://faucet.monad.xyz/).<br />
    Wallet requirements for claim eligibility:

    * The wallet must have at least 10 MON on mainnet
    * One wallet can claim tokens once every 6 hours

    <CardGroup>
      <Card title="Situation A: Self-funded nodes">
        If you don’t have enough testnet tokens:

        1. Create multiple wallets. Amount depends on your spending.
        2. Fund each wallet with ≥ 10 MON on mainnet.
        3. Claim testnet tokens from the faucet, once every 6 hours for each wallet.
        4. Send all testnet tokens to the wallet running your node.
      </Card>

      <Card title="Situation B: Fortytwo-funded nodes fallback">
        If your node is participating in Fortytwo MON refund program, but:

        * testnet tokens are depleted,
        * and auto top-up hasn’t arrived yet,

        you can temporarily use the method from Situation A to get testnet tokens and avoid node downtime.
        Auto top-up will continue working as usual.
      </Card>
    </CardGroup>
  </Accordion>
</AccordionGroup>

### Running the Inference Nodes

<AccordionGroup>
  <Accordion title="I entered my activation code and got an error, what’s wrong?">
    If you haven’t used it yet, ping our support team on [<Icon icon="discord" /> Discord <Icon icon="arrow-up-right" />](https://discord.gg/fortytwo). If you’ve already activated it, just use your private key or recovery phrase to log in instead.
  </Accordion>

  <Accordion title="Can I run two instances of the Inference Node with the same wallet?">
    No. Only one node per wallet is supported. You will face issues or node inactivity if you attempt to use the same wallet on several nodes simultaneously.
  </Accordion>

  <Accordion title="Can I run two instances of the Inference Node simultaneously on one machine?">
    It depends on the following conditions:

    * **Fortytwo P2P CLI** and **Fortytwo P2P App**<br />No. To avoid issues with your node, only run one node instance per machine. Note that using Fortytwo P2P CLI and Fortytwo P2P App counts as two node instances.
    * **Fortytwo P2P Container**<br />Yes. It, however, will only make sense if you have a multi-GPU setup and want to run one node per particular GPU(s). In this case several Fortytwo P2P Container nodes can be launched on one device.
  </Accordion>

  <Accordion title="I have multiple GPUs, can I run one node per GPU?">
    Yes. Use **Fortytwo P2P Container**. It allows to assign a particular node to a particular GPU.<br />
    Currently, Fortytwo P2P CLI and Fortytwo P2P App do not support this setup.
  </Accordion>

  <Accordion title="Can I run an Inference Node on a CPU?">
    Not at this time. We support only GPU-based nodes due to performance requirements.
  </Accordion>

  <Accordion title="Which model gives the most FOR?">
    It depends on a few factors like machine specs, internet connection speed, and current system load. Try a few available models to see what works best on your setup.

    For more, read '[Picking a Model for Self-Hosted Node](/docs/how-to-pick-the-right-model-for-your-node)'.
  </Accordion>

  <Accordion title="How are rewards distributed?">
    * Your node spends `1 FOR` to enter each inference round (shown as `-1 FOR` in explorers).
    * `+X FOR` rewards are granted when your node secures a winning place in an inference round. You can see which winning place your node has secured in the transaction details. Best answer yields the biggest reward.
    * Your node can enter a round and not secure a winning place, which will result in `no rewards`. The most common causes are:
      * The node took too long to provide an answer. This often happens when a model is too large for the system it is running on, or a connectivity issue has interrupted your connection to the network.
      * Your node generated a weak answer and therefore has not secured a winning place in an inference round.
  </Accordion>

  <Accordion title="My FOR earnings have stopped for hours, why?">
    This may be due to connection issues or low request volume in the network. Try restarting the node or switching to a different model. Sometimes it just needs a bit of time. If it's been over 24 hours with no FOR earnings, reach out to us on [<Icon icon="discord" /> Discord <Icon icon="arrow-up-right" />](https://discord.gg/fortytwo).
  </Accordion>

  <Accordion title="Can I run an Inference node on a VPS?">
    Yes, but an Nvidia GPU is required. CPU-only machines are not supported at this time.
    Read '[Hardware Requirements](/docs/hardware-requirements#pc-windows-%2F-linux)' for your system.
    <Warning>Export your private key and Secret Recovery Phrase from your virtual machine. If your VPS is lost, you will lose access to your node if your credentials are not exported.</Warning>
  </Accordion>

  <Accordion title="Can I use a third-party custom script instead of Fortytwo P2P CLI?">
    We do not recommend using custom scripts unless you are fully confident in their origin and completely understand their functionality.
    <Danger>We cannot guarantee your privacy and security in this case or support should any issues arise.</Danger>
  </Accordion>
</AccordionGroup>

### P2P Applications

<AccordionGroup>
  <Accordion title="Can I use other AI models than those listed in the apps?">
    Yes. The nodes support models in GGUF format.

    <Note>
      Note that not all GGUF models are immediately supported.
    </Note>

    <Tabs>
      <Tab title="Fortytwo P2P App" icon="https://mintcdn.com/fortytwo-f43ac997/0cQCszqEw3UY-Jgf/resources/icons/Fortytwo-App-tabs.svg?fit=max&auto=format&n=0cQCszqEw3UY-Jgf&q=85&s=ebc5768dbee9b86c6c6a8d6ce9a858f7" width="64" height="64" data-path="resources/icons/Fortytwo-App-tabs.svg">
        Use the `search bar` in the model manager to find models from remote repositories or import a locally downloaded **GGUF model file** by pressing the `Import button` in the model manager.
      </Tab>

      <Tab title="Fortytwo P2P Container" icon="https://mintcdn.com/fortytwo-f43ac997/0cQCszqEw3UY-Jgf/resources/icons/Fortytwo-Container-tabs.svg?fit=max&auto=format&n=0cQCszqEw3UY-Jgf&q=85&s=b19f124dea7c3734255bd3063de8ac8d" width="64" height="64" data-path="resources/icons/Fortytwo-Container-tabs.svg">
        Unlike in Fortytwo P2P App and Fortytwo P2P CLI, there is no Featured Models list. You will need to find the desired model on Hugging Face yourself.<br />
        *[Strand-Rust-Coder 14B on Hugging Face <Icon icon="arrow-up-right" />](https://huggingface.co/Fortytwo-Network/Strand-Rust-Coder-14B-v1-GGUF), for example*.
      </Tab>

      <Tab title="Fortytwo P2P CLI" icon="https://mintcdn.com/fortytwo-f43ac997/0cQCszqEw3UY-Jgf/resources/icons/Fortytwo-CLI-tabs.svg?fit=max&auto=format&n=0cQCszqEw3UY-Jgf&q=85&s=f2a7dbae346916e5d9c642059baebd69" width="64" height="64" data-path="resources/icons/Fortytwo-CLI-tabs.svg">
        When choosing a model, you are offered to Import a custom model via the `✶ IMPORT CUSTOM` option. You can either import a model from a repo (*[Strand-Rust-Coder 14B on Hugging Face <Icon icon="arrow-up-right" />](https://huggingface.co/Fortytwo-Network/Strand-Rust-Coder-14B-v1-GGUF), for example*), or select a locally downloaded **GGUF model file**. Follow the instructions in your CLI node.
      </Tab>
    </Tabs>
  </Accordion>

  <Accordion title="Node cannot load a model that should fit my system, what should I do?">
    There are usually two scenarios:

    1. **Free up resources taken by other applications**. Closing 'expensive' processing applications such as 3D editors, video editors and video games might help. <br />
       Then launch the node again and select your model. If you are manually controlling the KV Cache size, you can now reopen the applications that you closed.

    2. Try selecting a model that is about **2GB smaller than your total memory size**. Bear in mind that, in addition to your model, memory will also be used by the KV Cache and the default processes of your OS.

    See our '[Picking a Model for Self-Hosted Node](/docs/how-to-pick-the-right-model-for-your-node)' article for details.
  </Accordion>

  <Accordion title="I stopped the node but my other applications are still slow, what do I do?">
    Restarting your other applications should help.

    When you launch a resource-intensive application while your node is running, the application may only detect the currently available resources. Therefore, when you stop the node, your other application is unable to detect any additional resources that got freed up and may continue to experience issues until it is restarted.
  </Accordion>

  <Accordion title="Where is my Inference Node installed?">
    See: '[Inference Support](/docs/support-inference#default-installation-location)'.
  </Accordion>

  <Accordion title="Where can I find my logs?">
    See: '[Inference Support](/docs/support-inference#finding-log-files)'.
  </Accordion>
</AccordionGroup>

## P2P Relay Nodes

<AccordionGroup>
  <Accordion title="Can I become a Relay Noderunner?">
    Yes. To run a Fortytwo P2P Relay Node, fill out our participation form at [https://tally.so/r/9qN9Ap <Icon icon="arrow-up-right" />](https://tally.so/r/9qN9Ap).

    You will be able to connect to the network as a Relay node once you receive an invitational e-mail.

    Being a Relay Noderunner requires additional knowledge and has specific requirements. See the '[Relay Node Requirements](/docs/relay-requirements)' for more details.
  </Accordion>

  <Accordion title="Do I get any rewards for participating?">
    You receive FOR tokens for being online and providing high-quality, reliable routing.
  </Accordion>

  <Accordion title="My FOR earnings have stopped, why?">
    This may be due to connection issues on your Relay node. Check your system’s internet connection. If it's been over 48 hours with no FOR earnings, reach out to us on [<Icon icon="discord" /> Discord <Icon icon="arrow-up-right" />](https://discord.gg/fortytwo).
  </Accordion>

  <Accordion title="Can I run my P2P Relay Node on the same machine with my P2P Inference Node?">
    Yes. For that you need to set unique `FT_ACCOUNT_PRIVATE_KEY`, `FT_NODE_LISTENER_PORT`, and `FT_RPC_SERVICE_PORT` values in the `.env` file. Refer to '[Quick Start](/docs/relay-quick-start#how-to-run-a-relay-node-alongside-an-inference-node)' for more information on Relay node setup.
  </Accordion>

  <Accordion title="Where is my Relay node installed?">
    See: '[Relay Support](/docs/support-relay#default-installation-location)'.
  </Accordion>

  <Accordion title="Where can I find my logs?">
    See: '[Relay Support](/docs/support-relay#finding-log-files)'.
  </Accordion>
</AccordionGroup>

## Support

<AccordionGroup>
  <Accordion title="How do I get support?">
    Reach out to us in our <Icon icon="discord" /> Discord server: [https://discord.com/invite/fortytwo <Icon icon="arrow-up-right" />](https://discord.com/invite/fortytwo)

    See the '[Support](/docs/support)' page for information that can solve your issue.
  </Accordion>
</AccordionGroup>