lightningprox-openai

Drop-in replacement for the OpenAI SDK. Pay with Bitcoin Lightning instead of a credit card. No account required.

Install

npm install lightningprox-openai

Usage

// Before (OpenAI):
import OpenAI from 'openai'
const client = new OpenAI({ apiKey: process.env.OPENAI_API_KEY })

// After (Lightning):
import OpenAI from 'lightningprox-openai'
const client = new OpenAI({ apiKey: process.env.LIGHTNINGPROX_SPEND_TOKEN })

// Everything else stays identical:
const response = await client.chat.completions.create({
  model: 'claude-sonnet-4-6',
  messages: [{ role: 'user', content: 'Hello' }]
})
console.log(response.choices[0].message.content)

Two lines change. Nothing else does.

Alternatively, use any standard OpenAI SDK directly with base_url:

from openai import OpenAI
client = OpenAI(api_key=os.environ["LIGHTNINGPROX_SPEND_TOKEN"], base_url="https://lightningprox.com/v1")

import OpenAI from 'openai'
const client = new OpenAI({ apiKey: process.env.LIGHTNINGPROX_SPEND_TOKEN, baseURL: 'https://lightningprox.com/v1' })

Get a spend token

1. Go to lightningprox.com
2. Pay a Lightning invoice (any amount)
3. Receive your spend token (lnpx_...)
4. Set it as LIGHTNINGPROX_SPEND_TOKEN in your env

No account. No credit card. No KYC. Pay only for what you use.

Supported models

| Model | Provider | |-------|----------| | claude-opus-4-6 | Anthropic | | claude-sonnet-4-6 | Anthropic | | claude-haiku-4-5-20251001 | Anthropic | | gpt-4 | OpenAI | | gpt-4-turbo | OpenAI | | gpt-3.5-turbo | OpenAI | | gpt-4.1 | OpenAI | | gpt-4.1-mini | OpenAI | | gpt-4o | OpenAI | | gpt-4o-mini | OpenAI | | meta-llama/Llama-3.3-70B-Instruct-Turbo | Together.ai | | deepseek-ai/DeepSeek-V4-Pro | Together.ai | | Qwen/Qwen2.5-7B-Instruct-Turbo | Together.ai | | Qwen/Qwen3.5-397B-A17B | Together.ai | | mistral-large-latest | Mistral | | mistral-small-latest | Mistral | | mistral-medium-3-5 | Mistral | | gemini-2.5-flash | Google | | gemini-2.5-pro | Google |

Full list: lightningprox.com/api/capabilities

Error handling

try {
  const response = await client.chat.completions.create({ ... })
} catch (err) {
  if (err.code === 'insufficient_balance') {
    // err.status === 402
    // Top up at lightningprox.com
  }
  if (err.code === 'rate_limit_exceeded') {
    // err.status === 429
  }
}

Why

• No API keys to manage per provider — one spend token covers all models
• Pay only for what you use — no monthly plans, no minimums
• Switch models without changing auth
• Bitcoin-native — works anywhere Lightning works
• Two-line migration from existing OpenAI SDK code

Docs

lightningprox.com/docs

Built by LPX Digital Group LLC