PQS

active

Prompt Quality Score

Pre-flight prompt quality gate. Score any prompt 0–80 across 8 dimensions before inference. x402-native on Base.

AIBaseSolanax402 v2exactpromptqualityscore.com ↗︎

Settled via Coinbase.

Transactions · 30d
8
Volume · 30d
$0.056
Unique buyers · 30d
6
Uptime · 30d
100.0%
Latency p50
178ms
Reported calls · 30d
5

Endpoints (14 live)

  • POST /api/pqs-grade — 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. (0.001 USDC on Base)
  • POST /api/fix-injection — Detects prompt injections and returns a sanitized prompt. (0.025 USDC on Base)
  • POST /api/preflight — Scores prompts and endpoint trust before you spend on a paid LLM call. (0.05 USDC on Base)
  • POST /api/score/batch — Scores up to 10 prompts in one batch request. (0.25 USDC on Base)
  • POST /api/variants — Generates 1-5 ranked prompt rewrites scored on the 8-dimension PQS rubric. (0.1 USDC on Base)
  • POST /api/score — Scores prompts across 8 dimensions and suggests top fixes. (0.025 USDC on Base)
  • POST /api/score/compare/sol — PQS cross-model scoring — same prompt through Claude and GPT-4o, judged by a third model (Solana) (1.25 USDC on Solana)
  • POST /api/score/sol — PQS basic prompt score — grade, percentile, dimension breakdown (Solana) (0.025 USDC on Solana)
  • POST /api/proxy/venice — 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. (0.05 USDC on Base)
  • POST /api/score/compare — PQS cross-model scoring - same prompt through Claude and GPT-4o, judged by a third model (rev 2) (1.25 USDC on Base)
  • POST /api/score/batch/sol — PQS batch scoring — score up to 10 prompts in one call (Solana) (0.25 USDC on Solana)
  • POST /api/score/full/sol — PQS full analysis — optimized prompt plus before/after outputs (Solana) (0.125 USDC on Solana)
  • POST /api/preflight/sol — 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. (Solana variant) (0.05 USDC on Solana)
  • POST /api/score/full — PQS full analysis - optimized prompt plus before/after outputs (rev 2) (0.125 USDC on Base)

First seen · last seen · last active