Promptqualityscore

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.

Detect prompt injection (instruction override, role hijack, data exfiltration, delimiter attacks) and return a sanitized prompt

Basic PQS prompt score (8 dimensions, grade, top fixes)

Basic PQS prompt score (Solana x402)

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)

Preflight prompt + endpoint trust (Solana x402)

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.

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

Full PQS analysis: optimized prompt + before/after scoring + both outputs

Full PQS analysis (Solana x402)

Batch PQS scoring. Score up to 10 prompts in a single call.

Batch PQS scoring (Solana x402)

Cross-model scoring: Claude Sonnet 4 vs GPT-4o, judged by a third model

Cross-model scoring (Solana x402)