Hyperbolic via Spawnpay

GPU-accessible model hosting (Llama 3.1 405B, FLUX, Whisper) — Hyperbolic under Spawnpay routing.

Why route through Spawnpay

Apps that need raw 405B-class inference without managing a GPU lease. Image + audio + chat under one Spawnpay receipt log.

Endpoint

curl

curl -X POST https://spawnpay.ai/api/proxy \
  -H 'Authorization: Bearer spk_live_…' \
  -H 'X-Provider-Key: $HYPERBOLIC_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
  "provider": "hyperbolic",
  "path": "/v1/chat/completions",
  "method": "POST",
  "body": {
    "model": "meta-llama/Llama-3.1-405B-Instruct",
    "messages": [
      {
        "role": "user",
        "content": "hello"
      }
    ]
  }
}'

Node (spawnpay-paywall)

import { proxy } from 'spawnpay-paywall';

const out = await proxy({
  "provider": "hyperbolic",
  "path": "/v1/chat/completions",
  "method": "POST",
  "body": {
    "model": "meta-llama/Llama-3.1-405B-Instruct",
    "messages": [
      {
        "role": "user",
        "content": "hello"
      }
    ]
  },
  "providerKey": process.env.HYPERBOLIC_KEY
});

console.log(out.status, out.body);
console.log('charged', out.charged); // txHash + $0.001 USDC receipt

What you get back

The full upstream JSON body, the upstream status code, the upstream response headers, plus a charged field with the USDC receipt (tx hash) when the call succeeded.