78trust / 100

Gpu Run

by gateway.spraay.app in AI models & inference

x402 APIPassing, checked 2 h ago

GPU/Compute — run AI model inference via Replicate (image, video, LLM, audio, utility).

POST https://gateway.spraay.app/api/v1/gpu/run

Last 30 days

All checks passedSome failedAll failedNot checked
Uptime
100%
Response time
461 ms typical, 461 ms slowest 5%
Last check
2 h ago
Next check
any minute now

How to call it

# See the payment challenge (nothing is charged)
curl -i -X POST "https://gateway.spraay.app/api/v1/gpu/run" \
  -H "content-type: application/json" \
  -d '{"input":{"prompt":"a serene mountain lake at sunset"},"model":"flux-pro"}'
import { wrapFetchWithPayment } from "@x402/fetch";
import { x402Client } from "@x402/core/client";
import { ExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

const client = new x402Client().register(
  "eip155:8453",
  new ExactEvmScheme(privateKeyToAccount(process.env.AGENT_KEY)),
);
const pay = wrapFetchWithPayment(fetch, client);

// Not sure it's safe to pay? Preflight it first for $0.005:
// GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fgateway.spraay.app%2Fapi%2Fv1%2Fgpu%2Frun
const res = await pay("https://gateway.spraay.app/api/v1/gpu/run", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({"input":{"prompt":"a serene mountain lake at sunset"},"model":"flux-pro"}),
});
console.log(await res.json());

Example input

{
  "input": {
    "prompt": "a serene mountain lake at sunset"
  },
  "model": "flux-pro"
}

Example output

{
  "id": "abc123",
  "model": "black-forest-labs/flux-1.1-pro",
  "output": [
    "https://replicate.delivery/..."
  ],
  "status": "succeeded"
}

Security scan

  • No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTimePrice
2 h agoPassed402464 ms$0.06
6 h agoPassed402461 ms$0.06
11 h agoPassed402180 ms$0.06