Ai Classify

Last 30 days

Uptime

100%

Response time

85 ms typical, 85 ms slowest 5%

Last check

28 min ago

Next check

in 4 min

How to call it

# See the payment challenge (nothing is charged)
curl -i -X POST "https://agentbit.app/v1/ai/classify" \
  -H "content-type: application/json" \
  -d '{"labels":["billing","bug","feature_request","praise"],"text":"My payment failed and I was charged twice."}'

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%2Fagentbit.app%2Fv1%2Fai%2Fclassify
const res = await pay("https://agentbit.app/v1/ai/classify", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({"labels":["billing","bug","feature_request","praise"],"text":"My payment failed and I was charged twice."}),
});
console.log(await res.json());

Example input

{
  "labels": [
    "billing",
    "bug",
    "feature_request",
    "praise"
  ],
  "text": "My payment failed and I was charged twice."
}

Example output

{
  "confidence": "high",
  "label": "billing",
  "scores": {
    "billing": 0.94,
    "bug": 0.4,
    "feature_request": 0.02,
    "praise": 0
  }
}

Security scan

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

Recent checks