1 agent-payable API. Every listing carries a tested call recipe - endpoint, auth shape, pricing, and known gotchas - on its detail page. onchainintel.net ↗
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.