Pqs Grade
by promptqualityscore.com in AI models & inference
Quick pre-flight quality score: composite (0-100) + grade (A-F) + three framework sub-scores (PEEM, RAGAS, G-Eval) + verdict. Run upstream of any other paid call to filter weak prompts before inference. The cheapest gate on the AI input quality problem.
https://promptqualityscore.com/api/pqs-grade- Price
- $0.001
- per call in USDC
- Uptime
- 100%
- last 30 days
- Response time
- 988 ms
- 1.2 s slowest 5%
- Last check
- Passed
- 5 h ago, next any minute now
Reliability
Status and outage history · Atom feed · Watch with other listings
How to call it
POST https://promptqualityscore.com/api/pqs-grade
Each call costs $0.001 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://promptqualityscore.com/api/pqs-grade
content-type: application/json
{
"prompt": "Explain PQS scoring in one sentence to an AI agent operator.",
"vertical": "general"
}Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
prompt | string | Yes | Prompt text to grade (1-10000 chars) |
vertical | string | No | Optional domain: software/content/business/education/science/crypto/general/research One of: software, content, business, education, science, crypto, general, research. Default: "general". |
Example response
The provider's example. We can't check it without paying.
{
"frameworks": {
"geval": 6,
"peem": 5.5,
"ragas": 5.7
},
"grade": "C",
"methodology_url": "https://promptqualityscore.com/blog/five-framework-synthesis?utm_source=pqs-grade&utm_medium=api&utm_campaign=2026-05-grade-launch",
"score": 58,
"upgrade_url": "https://promptqualityscore.com/pro?utm_source=pqs-grade&utm_medium=api&utm_campaign=2026-05-grade-launch",
"verdict": "PEEM flags weak output format and role definition. Specify how the answer should be shaped and who is asking."
}Call it from code
The curl command shows the payment challenge. The JavaScript and Python versions pay and call, and never pay more than $0.001.
curl: see the payment challenge
# bash or zsh: see the payment challenge. Nothing is charged.
curl -sS -g -i -X POST 'https://promptqualityscore.com/api/pqs-grade' \
-H 'content-type: application/json' \
--data-raw '{"prompt":"Explain PQS scoring in one sentence to an AI agent operator.","vertical":"general"}'
# 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://promptqualityscore.com/api/pqs-grade' \
-H 'content-type: application/json' \
--data-raw '{"prompt":"Explain PQS scoring in one sentence to an AI agent operator.","vertical":"general"}' \
| 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 $0.001 per call.
const client = new x402Client().setSpendControls({ maxAmountPerPayment: "$0.001" });
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 $0.001 per payment. GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fpromptqualityscore.com%2Fapi%2Fpqs-grade&method=POST
const res = await pay("https://promptqualityscore.com/api/pqs-grade", {
method: "POST",
headers: { "content-type": "application/json" },
body: JSON.stringify({
"prompt": "Explain PQS scoring in one sentence to an AI agent operator.",
"vertical": "general"
}),
});
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 $0.001 per call.
client = x402ClientSync().set_spend_controls({"max_amount_per_payment": "$0.001"})
register_exact_evm_client(client, EthAccountSigner(Account.from_key(os.environ["EVM_PRIVATE_KEY"])))
with x402_requests(client) as session:
res = session.post(
"https://promptqualityscore.com/api/pqs-grade",
json={
"prompt": "Explain PQS scoring in one sentence to an AI agent operator.",
"vertical": "general",
},
)
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 |
|---|---|---|---|---|
| 5 h ago | Passed | 402 | 956 ms | $0.001 |
| 10 h ago | Passed | 402 | 990 ms | $0.001 |
| 14 h ago | Passed | 402 | 1.0 s | $0.001 |
| 19 h ago | Passed | 402 | 979 ms | $0.001 |
| 24 h ago | Passed | 402 | 1.1 s | $0.001 |
Show 10 older checks
| 28 h ago | Passed | 402 | 1.0 s | $0.001 |
| 33 h ago | Passed | 402 | 390 ms | $0.001 |
| 37 h ago | Passed | 402 | 948 ms | $0.001 |
| 41 h ago | Passed | 402 | 1.0 s | $0.001 |
| 46 h ago | Passed | 402 | 654 ms | $0.001 |
| 2 days ago | Passed | 402 | 1.2 s | $0.001 |
| 2 days ago | Passed | 402 | 396 ms | $0.001 |
| 2 days ago | Passed | 402 | 1.1 s | $0.001 |
| 3 days ago | Passed | 402 | 1.0 s | $0.001 |
| 3 days ago | Passed | 402 | 990 ms | $0.001 |