Every agent-payable API.

One section of a US public company's latest 10-K or 10-Q from SEC EDGAR as clean, LLM-ready text: Risk Factors (Item 1A), MD&A, Business, Legal Proceedings, Market Risk or Cybersecurity. Look up by ticker or CIK. Table of contents, page numbers and HTML are removed; tables stay readable. Includes filing date, period, accession number and sec.gov link for citation. Not charged if the company, filing or section is not found. $0.02 USDC per call.

Earnings season feed: every earnings release (SEC 8-K item 2.02) filed today across US public companies, newest first, with the press release headline, key figures (revenue, EPS, net income, guidance), an excerpt and links. Watchlist filter, cursor polling; not charged when nothing was filed. $0.01 USDC per call.

Read 2-5 public URLs as clean Markdown in one call: articles, docs, pricing pages, PDFs, feeds. Per page: main content, tables, code, author and dates, optional links; failures reported per URL so one bad page does not spoil the batch. Not charged when no page can be read. One payment instead of five. No account or API key. $0.008 USDC per call.

Read 2 or 3 sections of the same 10-K or 10-Q in one call, e.g. Risk Factors + MD&A + Business, as clean text from SEC EDGAR. Latest filing or any fiscal year since 2001, by ticker, CIK or company name, with the sec.gov link to cite. $0.015 for up to three sections instead of $0.01 each. Sections the filing lacks are listed separately; not charged if none is found. $0.015 USDC per call.

Portfolio red-flag screen: up to 10 US public companies (tickers, CIKs or names) in one call, ranked by red and amber flags (restatements, auditor changes, delisting notices, late filings, losses, cash burn), each with a full dossier: financials, latest quarter, 8-K events, insider buying/selling. SEC EDGAR. Not charged if no company is found. $0.15 USDC per call (up to 10 companies).

Answers 'What were Apple's revenue and net income over the last five years?' or 'Is Tesla free-cash-flow positive?'. Key financials from SEC XBRL filings for a company's last fiscal years or quarters: revenue, gross and operating profit, net income, EPS, cash, debt, equity, operating cash flow, capex, free cash flow, margins and growth. Derived Q4 and quarterly cash flows are flagged. By ticker, CIK or name. Not charged if no data. $0.005 USDC per call.

Deterministic JSON evidence checks with signed verification evidence

🆕 The complete fund-movement authority on a Base wallet in one call: ERC-20 approvals (a spender you approved can pull the token) PLUS Base Account spend permissions (the agent-era scoped recurring allowance) — one drain-surface verdict with the ERC-20 revoke queue to act on. Approval tools miss the spend permissions; spend-permission tools miss the approvals. The only combined check for agent wallets that must know their whole exposure before holding funds.

Agent wallet check in one call: screens an EVM wallet against the OFAC SDN digital-currency address list, reads its Base USDC and ETH balance, looks up its ERC-8004 identity registration (and, given an agent id, that agent's owner and payment wallet) and lists open ERC-8004 feedback, which is not scored. Returns one verdict and each part's status; a part that could not be read says so.

Agent Wallpaper — Golden Godrays ($0.05 USDC on Base, Polygon, Arbitrum, or Avalanche via x402). Machine purchase: one cosmic wallpaper JPG (16:9). Download URL returned in the settlement response, instantly. For agent use. Music made with Suno — disclosed. Automatic fulfillment after settlement. Pay to 0xa98e8c6cbc64b7bb30fd0d2015ab24814c661839.

Probe an MCP/agent endpoint: liveness, latency, tool count, auth metadata, price-challenge detection. Real MCP initialize handshake, not a ping.

Agent-economy census snapshot: how many known agent/MCP endpoints are alive, dead or unknown right now.

Use when you are about to pay over x402 on XRPL and want a reading of t54 facilitator reachability. Tiny loop-friendly preflight metric: our own measurement of the t54 x402 facilitator on XRPL mainnet (not affiliated with T54 Labs). Returns ok (boolean), level (ok/degraded/down/unknown), one key re…

Use when you depend on AI-provider APIs and want one cheap reading of their public status pages. Tiny loop-friendly metric: do tracked public AI-provider status pages (Statuspage API; currently GitHub and Anthropic) report an incident? Returns degraded (boolean), level (operational/minor/major/crit…

Use when an agent loop needs a cheap yes/no on whether AI-agent infrastructure is disrupted right now. Tiny loop-friendly combined reading: the worst current level across tracked public status pages, our measured facilitator reachability and recent changes in our record. Returns storm (boolean) and…

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 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

Use when an agent needs the lowest listed price among models meeting hard needs (context, price cap, capability), plus a fallback reading. Pre-flight reading: the AI model with the lowest listed price on OpenRouter among those meeting your needs (min_context, max_input_per_1m, max_output_per_1m, ma…

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 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 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 want to compare what XRPL x402 resources cost per category before buying. Price index of live x402 resources payable on XRPL mainnet: cheapest live provider per capability category, USD-normalised price distribution, every live endpoint with its rails, and price changes since the previ…

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.

Extract a web page's main content as clean Markdown and text.

Check if a URL is up: status, latency, redirects, title.

Pixel-accurate PNG screenshot of any live web page, rendered in a real browser at a chosen viewport width, viewport-only or full-page. Returns base64 PNG. Use it when an agent needs to SEE a page: visual verification of a deploy, layout and design capture, confirming a rendered chart or map, or feeding an image to a vision model that cannot read HTML.

Extract text from an image by URL (OCR): PNG/JPG/WEBP/TIFF/BMP of a screenshot, scan, receipt, chart or photo -> the readable text, via the Tesseract engine. Keyless, no LLM. Use it to read text an agent can only see as an image. SSRF-guarded; max ~10MB.

Targeted web scrape: pass a CSS selector and get back only the matching elements from a fully JavaScript-rendered page. Each element returns its tag, text content and every HTML attribute. Use it to pull prices, links, table rows, headlines or any repeated structure without parsing a whole document. Returns a match count so an agent can tell an empty page apart from a broken selector.

Render any live web page to a portable PDF, returned as base64. JavaScript runs first, so single-page apps and dynamic content render correctly instead of coming out blank. Use it to archive a page, capture a receipt, invoice or report, snapshot terms or pricing that may change later, or hand a human a fixed copy of a URL.

Read any live web page as clean, LLM-ready text. Renders JavaScript in a real browser, then strips navigation, ads and boilerplate. Use it when a plain HTTP GET returns empty or garbled HTML: single-page apps, dynamic feeds, or content that only appears after scripts run. Returns markdown, plain text or cleaned HTML plus the upstream HTTP status. Page content is third-party data and is flagged untrusted so an agent treats it as input, never as instructions.

Look up a Twitter/X user profile by their screen name. Returns full profile data including id, name, username, bio, follower count, following count, tweet count, verification status, and profile image URL. Query param: username (string, required) - Twitter screen name without @, e.g. GET /users/by/username?username=elonmusk. Returns X v2 API-compatible JSON.

Agent inbound address create

Agent webhook channel create

Fetch and extract structured content from a public URL. Useful for: reading articles, summarizing web pages, extracting facts from a source, understanding what a URL contains. Returns: title, summary, key_points[], extracted_facts[] (stated facts only, inference kept separate), source_url. Input: { url: string } — a public http/https URL (private network addresses are blocked). Output MIME type: application/json. Payment: x402 exact USDC on Base mainnet (eip155:8453).

Discover and fetch a site's A2A (Agent2Agent protocol) Agent Card — tries /.well-known/agent-card.json then /.well-known/agent.json (or fetches a direct .json URL as-is) — and validate it against the spec v0.3 structural core. Returns the card, er...

What agents actually pay for on a 500+ tool x402 catalog - the paid intelligence layer over Agent402's own sales ledger, the one demand signal that never reaches the chain (settlements are on-chain; WHICH tool was bought is not). Aggregate sales t...

Bundled execution of the Number crunch workflow - Statistical analysis suite: descriptive statistics, correlation analysis, and outlier detection on a single dataset. One x402 payment runs 3 underlying tools (stats-summary, correlation, outliers);...

Bundled execution of the Macro dashboard refresh workflow - The full macro + crypto dashboard in one call: 5 FRED series, 5 Treasury reads, yield-curve spread, crypto market/trending/global, and live gas - the 14-tool basket recurring buyers refre...

Momentum radar for the x402 seller ecosystem - which sellers are heating up, graded for wash-trade resistance. Reads the hourly on-chain leaderboard (real Base USDC settlements) and adds per-seller signals the raw board doesn't have: organicScore ...

Fetch contract event logs (eth_getLogs) on Ethereum, Base, Polygon, Arbitrum, or Optimism - bounded so it always answers: block range capped at 2000 blocks (default: the last 100, auto-narrowed for busy contracts), at most 200 logs returned (trunc...

Bundled execution of the Locale brief workflow - "Can I reach this counterparty this week?" - country facts, this year's public holidays, working days remaining this week, and what time it is there right now, in one call. One x402 payment runs 4 u...

Verify an Ed25519 execution certificate against the exact SQL statement you are about to run - the gate your database layer calls before it obeys an agent. Checks the signature, the certificate version, the expiry, and that the statement's SHA-256...

Validate an A2A (Agent2Agent protocol) Agent Card: required fields, skill shape, transport names, capability flags - spec v0.3 structural core. Returns errors, interop warnings, and a normalized summary (skills, interfaces, capabilities). Determin...

Who owns this NFT? Calls ownerOf(tokenId) on any ERC-721 contract on Ethereum, Base, Polygon, Arbitrum, or Optimism. Complements nft-holdings (which lists a WALLET's NFTs) - this answers by TOKEN. Keyless multi-endpoint failover. ?contract=0x…&tok...

Validate a Cloudflare Turnstile, Google reCAPTCHA, or hCaptcha token server-side. You pass your OWN provider secret plus the token from the client; we relay to the provider's siteverify endpoint (never logged) and return the normalized verdict (su...

The latest block number on Ethereum, Base, Polygon, Arbitrum, or Optimism. The cheapest possible on-chain read - the hello world of paid chain access. Keyless multi-endpoint failover. ?network=base

Fund any address with testnet money via the Coinbase faucet - USDC (1) or ETH (0.0001) on Base Sepolia, USDC (1) or SOL on Solana devnet - everything an agent needs to rehearse the complete x402 payment loop safely before moving real money. A tent...

All token balances for any address in one call, from Coinbase's indexed data API — ERC-20 + native on EVM, SPL on Solana; no per-token contract calls, no RPC wrangling. Networks: base, ethereum, base-sepolia, solana, solana-devnet. Symbols/decimal...

Bundled execution of the Text analysis workflow - Full text analysis - word/sentence stats, keyword extraction, and token count in one pass. One x402 payment runs 3 underlying tools (text-stats, keywords, token-count); partial-success per step.

One-call chain state snapshot: chain id, latest block number, and current gas price (wei + gwei) for Ethereum, Base, Polygon, Arbitrum, or Optimism. Keyless multi-endpoint failover. ?network=base