PQS - Prompt Quality Score

Score any LLM prompt for quality using PQS (Prompt Quality Score). Returns a grade (A-F), score out of 40, and percentile. Free tier — no payment required. Use this before sending any prompt to an LLM to check if it is worth running.

Score AND optimize any LLM prompt using PQS. Returns the original score, an optimized version of the prompt, and dimension-by-dimension breakdown across 8 quality dimensions based on PEEM, RAGAS, G-Eval, and MT-Bench frameworks. Costs $0.025 USDC via x402. Use this when you want to improve a prompt before running it.

Compare how Claude vs GPT-4o handles the same prompt using PQS. Both models are scored head-to-head by a third model judge. Returns winner, scores, and recommendation on which model to use for this prompt type. Costs $0.50 USDC via x402.