Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Pay-per-call Claude & GPT in Bitcoin sats

    1

    Your agent pays per call in sats. No signup, no credit card, no monthly bill. Claude, GPT, Gemini, DeepSeek and Mistral through one endpoint.

    Free

    Security scanned
    Pay-per-call Claude & GPT in Bitcoin sats

    Pay-per-call Claude & GPT in Bitcoin sats

    Example session with this skill installed

    Use LightningProx with gpt-4o-mini to explain in 3 short bullet points what the Bitcoin Lightning Network is good for. Use my spend token.

    • Read your context and instructions
    • Compiled the pay-per-call claude

    I sent this to gpt-4o-mini through LightningProx, billed to your spend token.

    Request summary

    FieldValue
    ProviderOpenAI (via LightningProx)
    Modelgpt-4o-mini
    Endpointhttps://lightningprox.com/v1/chat/completions
    BillingSpend token (X-Spend-Token)
    Sats charged5
    BalanceReturned with the response

    Answer

    Faster Transactions: The Lightning Network enables near-instantaneous transactions by allowing users to conduct off-chain transactions, significantly reducing the time it takes to confirm payments compared to the Bitcoin main chain.

    Lower Fees: By processing transactions off-chain, the Lightning Network minimizes transaction fees, making it more cost-effective for small payments or microtransactions, which might be impractical on the main blockchain due to higher costs.

    Scalability: The Lightning Network enhances Bitcoin's scalability by enabling a larger volume of transactions to be processed simultaneously, alleviating congestion on the main blockchain and allowing for increased usage without compromising speed or cost.

    Next steps

    • Want more depth? I can run the same question on a larger model such as Claude or Gemini; the cost is estimated before it runs.
    • You only pay for successful calls, and your remaining balance comes back with every response.
    • Top up anytime at https://lightningprox.com/topup.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Give your agent the major AI models without juggling provider API keys or a subscription.

    LightningProx is a Lightning-native inference gateway. Your agent sends a request, pays for exactly that request in sats, and gets the response. That's the whole loop.

    What you get

    • One endpoint for Claude, GPT, Gemini, DeepSeek and Mistral
    • Two ways to pay: per request over Lightning (L402), or a prepaid spend token you draw down
    • No account, no credit card, no monthly minimum
    • Capped spend: your agent can only spend what you load

    Good for

    • Agents that need a second model: a reviewer, a cheaper drafter, a different vendor
    • Bitcoin-native builders who'd rather pay in sats than open five provider accounts
    • Experiments where you want to pay for a handful of calls, not a plan

    What this skill does

    Teaches your agent to request, pay and call LightningProx end to end.

    Docs: https://lightningprox.com

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for APIs & Backend.

    No personal data in prompts. Minimum 5 sats per call. Requires Lightning wallet or funded lnpx token. Max 1 retry on failure with user consent.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 8 days ago

    • Free with an Agensi account

    Accounts
    Lightningprox

    Permissions

    Terminal / Shell
    Network Access
    Environment Variables

    Allowed Hosts

    lightningprox.com
    Listed8 days ago
    Updated5 days ago

    What's inside

    Frequently Asked Questions

    It acts as a unified gateway that replaces individual API keys with Bitcoin Lightning payments, allowing your agent to switch between providers like OpenAI and Anthropic without maintaining multiple pre-funded accounts or subscriptions.

    Yes, it is designed for any OpenAI-compatible SDK; you simply update the base_url to lightningprox.com and handle the L402 payment challenge or provide a spend token in the headers.

    Payments are handled via the L402 protocol, where the API returns a Lightning invoice (HTTP 402) that must be paid before the request is processed, or you can use a 'spend token' for automated, pre-authorized payments.

    No, there are no recurring costs; you only pay for the tokens you consume in Bitcoin sats, though there is a small minimum charge of 5 sats per request to cover network overhead.

    The skill includes the API integration logic, support for L402 challenge-response cycles, and a unified schema that allows your agent to call different models using a single message format.

    Updates to supported models (like new DeepSeek or GPT versions) are managed on the server side, so your agent will automatically have access to the latest IDs without requiring a manual skill update.

    New in APIs & Backend

    Free