Agent Weather
Use when you need conditions across a model category (reasoning, coding, vision-input...) with per-model job cost. Conditions across one category of AI models listed on OpenRouter (GET /v1/models/category/{name}; name one of reasoning, coding, vision-input, image-output, audio, retiring-soon, price-moved, free-tier): counts, price changes in the last 24h, new and removed models, models with an expiration date, vendor disturbances from the vendors' own status pages, and every model in the category with its standard job cost (10,000 input + 1,000 output tokens) as a plain fact. Categories come only from declared metadata, and the rule is stated in the response. Default order is by id; ?sort=cost orders by cost and is labelled "sorted by cost, not quality". Unknown categories get 400 before any payment. JSON. Example (illustrative): GET /v1/models/category/coding?sort=cost → {counts, price_movers_24h, models:[{id, standard_job_cost_usd}]}. Price: 0.01 RLUSD on XRPL mainnet (xrpl:0; RLUSD
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 2026-10-17.
Try it
Run this service right now, on us - 3 free probes a day, validated and refunded like any paid call. Query params optional.