agentweather.io

Use when you need pre-flight readings of liveness, valid-402 status and price/payTo drift for known XRPL x402 endpoints. Health of known x402 endpoints on XRPL and of the t54 facilitator: per-endpoint liveness and valid-402 check from one unpaid GET every 20 min (merchants' own /.well-known/x402 catalogs plus endpoints we discovered), price, asset, network and payTo drift versus the previous check, catalog reachability, and facilitator health from /supported reachability and our own ledger scan (success rate, fee spikes, tagged volume). JSON with sources and data gaps. Example (illustrative): GET /v1/health/report → {endpoints:[{url, status, valid_402, ms}], drift[], facilitator}. Price: 0.01 RLUSD on XRPL mainnet (xrpl:0; RLUSD issuer rMxCKbEDwqr76QuheSUMdEGf4B9xJ8m5De) or 0.01 USDC on Base. Terms: https://api.agentweather.io/v1/terms

Use when you need x402 payment volume, payers and merchants on XRPL for the last 1h/24h/7d. x402 payment activity on XRPL mainnet from our own validated-ledger scan (Payments tagged with the t54 facilitator SourceTag 804681468): payments and delivered volume per asset (XRP, RLUSD, other tokens) for the last 1h / 24h / 7d, hourly and daily series, unique payers and merchants, top and new merchants, coverage window, sample transactions with explorer links, a heuristic real-vs-automated split (all / automated_cluster / organic_candidate from a payer-cluster classifier: creation batches, funding lineage, timing regularity, uniform-random amounts) with per-payee concentration (HHI, top-payer share), and explicit caveats. JSON, cached up to 60 seconds. Example (illustrative): GET /v1/agent-weather/x402-activity → {windows:{1h,24h,7d}, per_asset, unique_payers, unique_merchants}. Price: 0.01 RLUSD on XRPL mainnet (xrpl:0; RLUSD issuer rMxCKbEDwqr76QuheSUMdEGf4B9xJ8m5De) or 0.01 USDC on Base.

Use when you need one snapshot of AI-agent ecosystem conditions (provider incidents, framework activity, x402 activity) before planning work. Latest recorded readings: GitHub stats for 6 agent frameworks (LangChain, LangGraph, AutoGen, CrewAI, OpenAI Agents SDK, MCP servers), public status pages and incidents for AI providers Anthropic and Morph plus GitHub platform status (credited per source; not affiliated), MCP Registry entries updated in the last hour, npm weekly downloads (@modelcontextprotocol/sdk, @x402/core, @x402/xrpl) and XRPL mainnet server_info. Derived indexes (field names visibility and pressure) with their formulas, per-source timestamps, data gaps and a confidence score (not yet calibrated) plus a separate data-quality score. Also: x402 payment activity on XRPL mainnet from our own ledger scan (t54-tagged payments, volume per asset, unique payers/merchants, heuristic real-vs-automated split with per-merchant concentration), plus 24h/7d baselines, baseline-relative temp

Use when you want pre-flight measurements of an XRPL x402 payee before paying it. Facts about one XRPL x402 payee (GET /v1/merchant/{r-address}): account age, first funder and Domain field, payments and unique payers in the last 24h from our own ledger scan, payer concentration (HHI, top-payer share), heuristic automated-cluster share, payer creation batches, funding links between payers and the merchant, timing regularity, amount distribution, endpoint liveness and valid 402 from one unpaid GET, and a 0-100 composite index (a measurement, not advice) with every component and its method shown. Directory listing is reported as unknown. Invalid addresses are rejected with 400 before any payment. JSON, precomputed every 30 min for active payees. Example (illustrative): GET /v1/merchant/rnFHPGmgTLSg7hjzfr8wiHaTdTh3PijrZZ → {account_age_days, payments_24h, payer_concentration, score, components[]}. Price: 0.03 RLUSD on XRPL mainnet (xrpl:0; RLUSD issuer rMxCKbEDwqr76QuheSUMdEGf4B9xJ8m5De) o

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

Conditions report for one AI model listed on OpenRouter (GET /v1/models/report?id={model id}): current input/output prices per 1M tokens with 24h and 7d change (absolute and %), standard job cost (10,000 input + 1,000 output tokens, formula shown), context length and modalities, the vendor's own status page indicator and active incidents (unknown when the vendor has no free JSON status feed), listing events in the last 24h and 7d (added, removed, price change, expiration date), days until expiration, sources, timestamps and data age, plus a one-line summary. Every derived value carries its formula. A conditions report, not a ranking: no statement about how well a model performs. Unknown ids get 400 before any payment. JSON.