82trust / 100

Classify

by NetIntel in AI models & inference

x402 APIPassing, checked 3 h ago

Classify text into your own categories — zero-shot: supply 2–20 labels and Claude Haiku returns the best-matching category with confidence and per-label scores. Route, tag, triage, and detect intent or topic with your own taxonomy in one call.

POST https://netintel.dev/classify

Last 30 days

All checks passedSome failedAll failedNot checked
Uptime
100%
Response time
181 ms typical, 181 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://netintel.dev/classify" \
  -H "content-type: application/json" \
  -d '{"labels":["billing","technical","general"],"text":"Hi, I was charged twice for my subscription this month and need a refund."}'
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%2Fnetintel.dev%2Fclassify
const res = await pay("https://netintel.dev/classify", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({"labels":["billing","technical","general"],"text":"Hi, I was charged twice for my subscription this month and need a refund."}),
});
console.log(await res.json());

Example input

{
  "labels": [
    "billing",
    "technical",
    "general"
  ],
  "text": "Hi, I was charged twice for my subscription this month and need a refund."
}

Example output

{
  "confidence": 0.91,
  "findings": [],
  "grade": "A",
  "label": "billing",
  "labels_provided": [
    "billing",
    "technical",
    "general"
  ],
  "mode": "single_label",
  "score": 100,
  "scores": {
    "billing": 0.91,
    "general": 0.03,
    "technical": 0.06
  }
}

Security scan

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

Recent checks

WhenResultHTTPTimePrice
3 h agoPassed402181 ms$0.005