83trust / 100

Sandbox Create

by BlockRun.AI in AI models & inference

x402 APIPassing, checked 3 h ago

Create a managed Python 3.11 sandbox. Two billing modes selected by 'timeout': ≤300s = flat rate (CPU $0.01, GPU varies). >300s = per-hour billing for the full requested lifetime, no refund on early terminate. Max 24h.

POST https://blockrun.ai/api/v1/modal/sandbox/create

Last 30 days

All checks passedSome failedAll failedNot checked
Uptime
100%
Response time
178 ms typical, 178 ms slowest 5%
Last check
3 h ago
Next check
any minute now

How to call it

# See the payment challenge (nothing is charged)
curl -i -X POST "https://blockrun.ai/api/v1/modal/sandbox/create" \
  -H "content-type: application/json" \
  -d '{}'
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 $0.03:
// GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fblockrun.ai%2Fapi%2Fv1%2Fmodal%2Fsandbox%2Fcreate
const res = await pay("https://blockrun.ai/api/v1/modal/sandbox/create", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({}),
});
console.log(await res.json());

Example output

{
  "result": {}
}

Security scan

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

Recent checks

WhenResultHTTPTimePrice
3 h agoPassed402178 ms$0.011