跳到正文
TakoAPI
返回技能列表

lightningprox

由 unixlamadev-spec 提供

Browser & Automation
481下载量由 clawskills.sh 提供
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

Pay-per-request AI model access via Bitcoin Lightning using prepaid spend tokens.

描述

该技能的功能

Pay-per-use AI gateway that routes requests to 19 models across Anthropic, OpenAI, Together.ai, Mistral, and Google via Bitcoin Lightning micropayments. Authentication works through a prepaid spend token or per-request Lightning invoice. No provider accounts or API keys required.

Eliminates the need to create accounts and manage separate billing with each AI provider.

何时使用

  • Running AI inference without managing multiple provider API keys
  • Comparing the same prompt across Claude, GPT-4, and Gemini in one tool
  • Paying for one-off agent tasks with Bitcoin sats
  • Using Pixtral vision or Codestral code models without a Mistral account
  • Building autonomous agents that self-fund inference via Lightning payments

示例工作流

输入

User asks: send a prompt to claude-opus-4-5-20251101 using a spend token

智能体
  1. 1

    Read LIGHTNINGPROX_SPEND_TOKEN from environment

  2. 2

    POST to lightningprox.com/v1/messages with model and message payload

  3. 3

    Set X-Spend-Token header for authentication

  4. 4

    Receive response and return model output

输出

Claude's reply to the prompt, with cost deducted in satoshis from the prepaid token balance

前置要求

  • LIGHTNINGPROX_SPEND_TOKEN environment variable (top up at lightningprox.com by paying a Bitcoin Lightning invoice)

安装

clawhub install unixlamadev-spec/lightningprox

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接