PQS - A Quality Gate For Prompts

external

A Quality Gate For Prompts. Before they break production. Score any AI prompt against 8 dimensions, see what's weak, and get the fixed version in seconds.

by Promptqualityscore9 endpoints100% uptime132ms avg

Price

from $0.0010

up to $1.25 per request

Network

base

Base URL

https://promptqualityscore.com

Endpoints (9)

Discovered from on-chain x402 payment activity. Prices shown are per-call in USDC.

POST/api/fix-injection

base$0.0250

PQS injection detection - heuristic + LLM verdict on prompt-injection attempts with sanitized output

POST/api/pqs-grade

base$0.0010

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.

POST/api/preflight

base$0.0500

Pass/Fail before you waste budget on a doomed call. Decide whether to make a paid LLM call before you make it. Preflight scores your prompt against an 8-dimension quality rubric (pass/fail at 28/80) and optionally pulls the target endpoint's on-chain trust signals — total payments, unique payers, last activity. Two-in-one circuit breaker for agents that don't want to waste budget on weak prompts or sketchy endpoints. (rev 2)

POST/api/proxy/venice

base$0.0500

Venice.ai chat completion with PQS preflight scoring. Returns LLM response plus 8-dimension quality score in one paid call. No signup, no API key.

POST/api/score

base$0.0250

PQS score - 8-dimensional prompt quality breakdown across 5 frameworks with top fixes

POST/api/score/batch

base$0.2500

PQS batch scoring - score up to 10 prompts in one call (rev 2)

POST/api/score/compare

base$1.25

PQS cross-model scoring - same prompt through Claude and GPT-4o, judged by a third model (rev 2)

POST/api/score/full

base$0.1250

PQS full analysis - optimized prompt plus before/after outputs (rev 2)

POST/api/variants

base$0.1000

PQS variants - N ranked prompt rewrites scored on the 8-dimension rubric, returned best-first

Payment

Protocolx402 (direct payment, USDC)

Networkbase

Pay to0xb40a...1308

How to call

Via APIHub (recommended)No wallet · pay with credits · gasless

# one-time setup
npx @apihubio/cli register
npx @apihubio/cli topup 10

# call it
npx @apihubio/cli call https://promptqualityscore.com \
  -X POST \
  -d '{ /* check provider docs for input */ }'

# or save it to Claude/Cursor/Codex
npx @apihubio/cli install
npx @apihubio/cli add https://promptqualityscore.com

APIHub pays the provider on your behalf and debits your credit balance for the exact amount. No wallet setup, no gas, no per-call signing.

Via direct x402 (advanced)Bring your own wallet

import { wrapFetchWithPayment } from "@x402/fetch";
import { createWalletClient, http } from "viem";
import { privateKeyToAccount } from "viem/accounts";
import { base } from "viem/chains";

const account = privateKeyToAccount("0xYOUR_PRIVATE_KEY");
const client = createWalletClient({ account, chain: base, transport: http() });
const x402Fetch = wrapFetchWithPayment(client);

const res = await x402Fetch("https://promptqualityscore.com", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({ /* check provider docs for input */ }),
});
const data = await res.json();

Requires USDC on Base and gas on each call. The @x402/fetch client signs EIP-3009 transferWithAuthorization for each 402 response and retries.

This is an external service not operated by APIHub. Listing data is sourced from public on-chain records and third-party indexes. Payment goes directly to the service provider via the x402 protocol. APIHub does not guarantee availability, accuracy, or quality of external services.