Llm

Last 30 days

Uptime

100%

Response time

405 ms typical, 433 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://twin.unykorn.org/llm" \
  -H "content-type: application/json" \
  -d '{"params":{"max_tokens":200,"messages":[{"content":"Summarise the x402 payment flow in three sentences.","role":"user"}],"model":"qwen2.5:7b"}}'

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%2Ftwin.unykorn.org%2Fllm
const res = await pay("https://twin.unykorn.org/llm", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({"params":{"max_tokens":200,"messages":[{"content":"Summarise the x402 payment flow in three sentences.","role":"user"}],"model":"qwen2.5:7b"}}),
});
console.log(await res.json());

Example input

{
  "params": {
    "max_tokens": 200,
    "messages": [
      {
        "content": "Summarise the x402 payment flow in three sentences.",
        "role": "user"
      }
    ],
    "model": "qwen2.5:7b"
  }
}

Example output

{
  "finish_reason": "stop",
  "model": "qwen2.5:7b",
  "ok": true,
  "output": "<assistant text>",
  "provider": "ollama-local",
  "receipt": {
    "amount_usd": 0.003,
    "receipt_id": "g402-<16hex>",
    "tx_hash": "0x<64hex>"
  },
  "type": "llm",
  "usage": {
    "completion_tokens": 88,
    "prompt_tokens": 42
  }
}

Security scan

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

Recent checks