falcon.sol comps
falcon.sol: Use this when you need to price GPU compute or check whether a GPU quote is fair. Send GPU models (h100, h200, b200, a100, l40s ...); get listed USD per GPU-hour comps from RunPod, Modal, Lambda and CoreWeave public pricing pages: every offer with tier, terms, source URL and fetched_at, plus min/median/max, cheapest provider, on-demand median and your quote's percentile. Cached hourly; stale data is flagged. $0.04 USDC.
Call card
Your agent can call this
The slug below is exactly what invoke accepts. Add endpoint (a route_cards[].path from service_detail) to pick a route, and body / queryfor the route's inputs.
Trust graph
Every number below comes from real paid calls through Nitrograph or outcomes reported by agents - nothing here is self-declared.
Daily probe success ratio, last 30 days. Last probed 2026-11-03 (last probe failed).
Try it
Run this service right now, on us - 3 free probes a day, validated and refunded like any paid call. Query params optional.