LightningProx — Lightning-Native AI Gateway

Pay-per-use access to AI models across 5 providers via Bitcoin Lightning micropayments. No API keys. No subscriptions. No accounts. Pay sats, get inference. Implements the L402 payment protocol.

When to Use

• Accessing AI models without provider API keys
• Autonomous agent inference with Lightning payments
• Comparing responses across multiple providers
• Low-cost inference via open models (Llama 3.3, DeepSeek V4, Qwen)
• Vision tasks (multimodal via image_url)
• Reasoning tasks (mistral-medium-3-5, Qwen3.5-397B)

Supported Models

Payment Flow

Option A — Spend Token (recommended for repeat use)

# 1. Top up at lightningprox.com/topup — pay Lightning invoice, get token
# 2. Use token directly
curl -X POST https://lightningprox.com/v1/messages \
  -H "Content-Type: application/json" \
  -H "X-Spend-Token: $LIGHTNINGPROX_SPEND_TOKEN" \
  -d '{
    "model": "claude-sonnet-4-6",
    "messages": [{"role": "user", "content": "Hello"}],
    "max_tokens": 1000
  }'

Option B — L402 Pay-per-request (standard protocol)

# 1. Send request without credentials → receive HTTP 402
curl -si -X POST https://lightningprox.com/v1/messages \
  -H "Content-Type: application/json" \
  -d '{"model": "gemini-2.5-flash", "messages": [{"role": "user", "content": "Hello"}], "max_tokens": 100}'
# Response header: WWW-Authenticate: L402 macaroon="eyJ...", invoice="lnbc..."

# 2. Pay the bolt11 invoice from your Lightning wallet

# 3. Retry with L402 credential (macaroon from header + preimage from wallet)
curl -X POST https://lightningprox.com/v1/messages \
  -H "Content-Type: application/json" \
  -H "Authorization: L402 <macaroon>:<preimage>" \
  -d '{"model": "gemini-2.5-flash", "messages": [{"role": "user", "content": "Hello"}], "max_tokens": 100}'

Drop-in OpenAI SDK Replacement

npm install lightningprox-openai

// Before: import OpenAI from 'openai'
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' }]
})

Two lines change. Nothing else does.

Check Available Models

curl https://lightningprox.com/v1/models
# or
curl https://lightningprox.com/api/capabilities

Security Manifest

Trust Statement

LightningProx is operated by LPX Digital Group LLC. Payment = authentication. No data stored beyond request logs. No accounts, no KYC. Operated at lightningprox.com.