Classify Zero Shot

Last 30 days

Uptime

100%

Response time

276 ms typical, 356 ms slowest 5%

Last check

5 min ago

Next check

in 24 min

How to call it

# See the payment challenge (nothing is charged)
curl -i -X POST "https://tanod.dev/v1/classify/zero-shot" \
  -H "content-type: application/json" \
  -d '{"labels":["billing","technical support","sales"],"text":"I was charged twice for my subscription this month."}'

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%2Ftanod.dev%2Fv1%2Fclassify%2Fzero-shot
const res = await pay("https://tanod.dev/v1/classify/zero-shot", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({"labels":["billing","technical support","sales"],"text":"I was charged twice for my subscription this month."}),
});
console.log(await res.json());

Example input

{
  "labels": [
    "billing",
    "technical support",
    "sales"
  ],
  "text": "I was charged twice for my subscription this month."
}

Example output

{
  "hypothesis_template": "This example is about {}.",
  "labels": [
    {
      "label": "billing",
      "score": 0.941569
    },
    {
      "label": "sales",
      "score": 0.054991
    },
    {
      "label": "technical support",
      "score": 0.00344
    }
  ],
  "model": {
    "id": "nli-deberta-v3-xsmall",
    "license": "Apache-2.0",
    "revision": "a150876415327c80daeff35ca6f68f5ed8cf5c24",
    "source": "cross-encoder/nli-deberta-v3-xsmall"
  },
  "multi_label": false,
  "note": "English NLI model; scores are model confidences, not calibrated probabilities",
  "truncated": false,
  "usage": {
    "labels": 3,
    "tokens": 58
  }
}

Security scan

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

Recent checks