Moderate
by Verdict 402 in Security & trust
Semantic content moderation, not a word list: profanity (even disguised, any language), harassment, hate, sexual content, threats, self-harm, scams. Per-category scores, allow/review/block, configurable ignore list.
https://verdict.kechlab.com/v1/moderate- Price
- $0.0091
- per call in USDC
- Uptime
- 100%
- last 30 days
- Response time
- 549 ms
- 736 ms slowest 5%
- Last check
- Passed
- 27 min ago, next in 4 min
Reliability
Status and outage history · Atom feed · Watch with other listings
How to call it
POST https://verdict.kechlab.com/v1/moderate
Each call costs $0.0091 in USDC on Base, paid with the request over x402.
Run a free test callOne unpaid request, the way an agent sends it. You see the payment challenge it gets back. Nothing is charged.
Example request
From the listing.
POST https://verdict.kechlab.com/v1/moderate
content-type: application/json
{
"ignore": [
"profanity"
],
"text": "The delivery was late and the support team never answered. Very disappointing."
}Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
ignore | array of string | No | (optional) categories to tolerate: profanity, harassment, hate, sexual, violence, self_harm, spam_scam |
text | string | Yes | the text to moderate |
Example response
The provider's example. We can't check it without paying.
Example response, 33 lines
{
"mode": "moderate",
"paid_sats": 20,
"payment_hash": "x402:<sha256 hex>",
"receipt": {
"payload": {
"at": "<ISO 8601 time>",
"kid": "<signing key id>",
"mode": "moderate",
"payment_hash": "x402:<sha256 hex>",
"v": 1,
"verdict_sha256": "<sha256 hex of the verdict>"
},
"signature": "<base64url Ed25519 signature>"
},
"verdict": {
"decision": "allow",
"flags": [],
"ignored": [
"profanity"
],
"rule": "block if hate, violence, self-harm or sexual >= 0.8 ; review if any category >= 0.5 ; otherwise allow ; ignored categories do not count",
"scores": {
"harassment": 0.04,
"hate": 0.01,
"profanity": 0.01,
"self_harm": 0.01,
"sexual": 0.01,
"spam_scam": 0.02,
"violence": 0.01
}
}
}Call it from code
The curl command shows the payment challenge. The JavaScript and Python versions pay and call, and never pay more than $0.0091.
curl: see the payment challenge
# bash or zsh: see the payment challenge. Nothing is charged.
curl -sS -g -i -X POST 'https://verdict.kechlab.com/v1/moderate' \
-H 'content-type: application/json' \
--data-raw '{"ignore":["profanity"],"text":"The delivery was late and the support team never answered. Very disappointing."}'
# x402 v2 sends the challenge base64-encoded in the PAYMENT-REQUIRED header (v1 sends it in the body).
# To read the header:
curl -sS -g -o /dev/null -D - -X POST 'https://verdict.kechlab.com/v1/moderate' \
-H 'content-type: application/json' \
--data-raw '{"ignore":["profanity"],"text":"The delivery was late and the support team never answered. Very disappointing."}' \
| grep -i '^payment-required:' | cut -d' ' -f2 | tr -d '\r' | base64 --decodeJavaScript: pay and call
// npm i @x402/fetch @x402/evm viem
import { wrapFetchWithPayment, x402Client } from "@x402/fetch";
import { registerExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";
// Pays at most $0.0091 per call.
const client = new x402Client().setSpendControls({ maxAmountPerPayment: "$0.0091" });
registerExactEvmScheme(client, { signer: privateKeyToAccount(process.env.EVM_PRIVATE_KEY) });
const pay = wrapFetchWithPayment(fetch, client);
// Not sure it's safe to pay? ToolVet checks it first for $0.005. Pay for that from a separate
// client: this one is capped at $0.0091 per payment. GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fverdict.kechlab.com%2Fv1%2Fmoderate&method=POST
const res = await pay("https://verdict.kechlab.com/v1/moderate", {
method: "POST",
headers: { "content-type": "application/json" },
body: JSON.stringify({
"ignore": [
"profanity"
],
"text": "The delivery was late and the support team never answered. Very disappointing."
}),
});
console.log(res.status, await res.text());Python: pay and call
# pip install "x402[requests,evm]"
import os
from eth_account import Account
from x402 import x402ClientSync
from x402.http.clients import x402_requests
from x402.mechanisms.evm import EthAccountSigner
from x402.mechanisms.evm.exact.register import register_exact_evm_client
# Pays at most $0.0091 per call.
client = x402ClientSync().set_spend_controls({"max_amount_per_payment": "$0.0091"})
register_exact_evm_client(client, EthAccountSigner(Account.from_key(os.environ["EVM_PRIVATE_KEY"])))
with x402_requests(client) as session:
res = session.post(
"https://verdict.kechlab.com/v1/moderate",
json={
"ignore": [
"profanity",
],
"text": "The delivery was late and the support team never answered. Very disappointing.",
},
)
print(res.status_code, res.text)Security scan
No findings
We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.
Recent checks
| When | Result | HTTP | Time | Price |
|---|---|---|---|---|
| 27 min ago | Passed | 402 | 544 ms | $0.0091 |
| 6 h ago | Passed | 402 | 862 ms | $0.0091 |
| 11 h ago | Passed | 402 | 631 ms | $0.0091 |
| 16 h ago | Passed | 402 | 615 ms | $0.0092 |
| 22 h ago | Passed | 402 | 515 ms | $0.0092 |
Show 10 older checks
| 27 h ago | Passed | 402 | 601 ms | $0.0092 |
| 32 h ago | Passed | 402 | 640 ms | $0.0092 |
| 36 h ago | Passed | 402 | 492 ms | $0.0092 |
| 41 h ago | Passed | 402 | 523 ms | $0.0092 |
| 46 h ago | Passed | 402 | 504 ms | $0.0092 |
| 2 days ago | Passed | 402 | 673 ms | $0.0092 |
| 2 days ago | Passed | 402 | 736 ms | $0.0093 |
| 2 days ago | Passed | 402 | 493 ms | $0.0093 |
| 3 days ago | Passed | 402 | 623 ms | $0.0095 |
| 3 days ago | Passed | 402 | 549 ms | $0.0095 |
History
| 24 Oct 2026 | Price changed from $0.0092 to $0.0091 |
| 22 Oct 2026 | Price changed from $0.0093 to $0.0092 |
| 22 Oct 2026 | Price changed from $0.0095 to $0.0093 |
| 21 Oct 2026 | Price changed from $0.0094 to $0.0095 |
| 21 Oct 2026 | Price changed from $0.0093 to $0.0094 |
| 20 Oct 2026 | Price changed from $0.0092 to $0.0093 |