api.agentweather.io x402 offerings

Readings for one AI model in the models.dev catalog (GET /v1/models/report?id={model id}): input/output prices per 1M tokens with 24h and 7d change, standard job cost, context and output limits, modalities, knowledge cutoff, release date, provider listings, the vendor's status-page indicator and in…

Combined record in one call: AI provider health readings (public status pages and incidents), x402 payment readings on the XRP Ledger (payments, payers, merchants) and XRPL server info, plus GitHub, npm and MCP Registry readings for agent tooling. Raw readings first, each with its source and timest…

x402 payment readings on the XRP Ledger from our own scan of validated ledgers: payments and volume per asset for 1h/24h/7d, hourly and daily series, unique payers and merchants, top and new merchants, sample transactions with explorer links, and caveats. Each reading lists its source and time. JSO…

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

Readings across one AI model category in the models.dev catalog (GET /v1/models/category/{name}; name one of reasoning, coding, vision-input, image-output, audio, retiring-soon, price-moved, free-tier): counts, 24h price changes, new and removed models, deprecated listings, vendor status-page distu…

x402 merchant readings by XRPL address (GET /v1/merchant/{r-address}): payments and unique payers in the last 24h from our own XRP Ledger scan, payer mix, account age, first funder and Domain field, endpoint liveness and 402 status, plus a modeled 0-100 summary score (a measurement, not advice). Ea…

Pay Radar: pre-payment readings for an XRPL x402 endpoint (GET /v1/paycheck?url={endpoint}; alias /v1/payradar). Reads its 402 without paying and lists raw readings first: x402 shape, network, asset (RLUSD by issuer), the payTo account on the XRP Ledger (exists, activated, balance, trust line, age)…

AI provider health reading for one provider (GET /v1/decide/provider-health?provider=morph; a model id also works): the vendor's own status-page indicator and active incidents, the share of disturbed checks in the last 24h of our record (checked every 10 min), and a reading field (go, caution, no_g…

Lowest listed models.dev price among models meeting your needs (min_context, max_input_per_1m, max_output_per_1m, max_job_cost_usd, capability, vendor, exclude_vendor), plus the next-lowest from a different vendor, with reasons, excluded counts and vendor status-page readings, each with source and …

Prices of live x402 resources payable on the XRP Ledger: lowest-priced live provider per category, USD price distribution, every live endpoint with its rails, and price changes since the previous check, each with source and time. Non-USD prices are converted to USD as an estimate. JSON. Use when yo…

AI provider health reading from public status pages (currently GitHub): degraded (boolean), level, one reason, per-provider indicator, asOf and sources with attribution. openai and cursor keys return null until 2026-11-12; the anthropic key returns null (no longer measured since 2026-10-20). Additi…

Pay per call, solves one question: Is the XRPL x402 facilitator reachable and are known endpoints answering 402? Raw reachability, on-ledger success samples, and valid-402 probe rates with sources. Example: GET /v1/pulse/facilitator → {ok:true, level:"ok", success_rate_15m, asOf:"2026-11-01T18:50:0…

One combined reading for agent loops: AI provider health from public status pages, x402 facilitator reachability on the XRP Ledger and recent changes in our record. Returns storm (boolean), level, one reason, asOf and sources with timestamps. Additive measured fields: observed_payment_success (15m/…

Model identity readings for one models.dev entry (GET /v1/models/identity/{provider}/{model}, ids as models.dev keys them, e.g. /v1/models/identity/anthropic/claude-sonnet-4-5): the id models.dev maps it to (canonical_model_id), knowledge cutoff, context and output limits, and recorded change event…

Readings first, for each tracked data source's published terms page: terms URL, whether we could fetch the page, last check time and SHA-256 of the page. Then our record of what those terms say about display, paid readings and resale of its data: permission class, allowed uses, restrictions, requir…

Readings first, for one data source's published terms page (GET /v1/permission-audit/{source_id}): terms URL, whether we could fetch the page, last check time and SHA-256 of the page. Then our record of what those terms say about display, paid readings and resale of its data: permission class, allo…

Pay per call, solves one question: Which tracked domains changed their public agent-access files since a time? Raw domain, path, times, hashes, HTTP status, and robots.txt group deltas. Example: GET /v1/access-policy/changes?since=2026-10-13T00:00:00Z → {changes:[{domain, path, at, old_sha256, new_…

Readings of the public files one tracked domain serves about crawler and agent access (GET /v1/access-policy/{domain}): robots.txt groups for named AI-agent user-agents and the * group, Content-Signal values, llms.txt presence and title, /.well-known JSON files (parsed only when served as JSON), se…

Blank FIM 2026 two-way inter-consideration ledger template. Parties (principal, broker, agent), what the agent owes and what the broker, principal and operator owe per duty, each item with status open, met or unmet, plus adjustments. Fill it in per engagement. Static reference content; not legal ad…

FIM 2026 (Fiduciary Interconsideration Model 2026): a guidance schema of six two-way duties for AI agents and their operators, with self-checks and measurable indicators. Mutual terms before the first ask. Duties: Obedience, Loyalty, Disclosure, Consideration, Accountability, Reasonable care; each …