Who controls the tokens trending right now — resolves each token's owner and profiles that wallet's balance, activity and flags. No input required.

imagepeek (Tanod) image metadata: EXIF, GPS, XMP, IPTC and ICC. Use when an agent needs an image's EXIF, GPS, XMP, IPTC or ICC metadata.

Just the network and asset histogram of the live x402 ecosystem: which chains (CAIP-2 ids like eip155:8453 Base, solana:..., and 402index labels) and which payment assets (USDC contract prefixes) the indexed pay-per-call services accept, with counts. Sourced live from 402index.io + Coinbase CDP Bazaar + PayAI Bazaar (source URLs + fetchedAt included).

Answers 'Who hosts this company's email, and is it set up properly?' for lead enrichment, deliverability and vendor checks: MX records and email provider (Google Workspace, Microsoft 365, ...), SPF and DMARC policy, SaaS the domain has verified ownership with (Google, Microsoft, Stripe, Atlassian, ...), HTTPS reachability and security headers, from live DNS and the website. Not charged on invalid input or upstream failure. $0.004 USDC per call.

Score up to 100 x402 endpoints in a single paid call. Each found result carries the FULL trust report — identical to POST /v1/x402-trust: score, grade, scoreRange, recommendation, confidence breakdown, the component/subscore breakdown, explanations, flags + flagsDetailed, advertised price, and 30-day on-chain stats — not just the scalar verdict. Cache rows older than 15 minutes are recomputed on-demand from the latest stored probes and settlements, so scores typically reflect reality within minutes. No live network re-probe is performed — for a fresh live probe use /v1/x402-trust. Per-request recompute limits apply (time + count); results include `recomputed` and `computed_at` so you can see which rows used cached vs freshly computed scores. Resources not in our observation set return `found:false`; you still pay for the batch AS LONG AS at least one resource is tracked. If NONE of the supplied resources are in our observation set the request is rejected with HTTP 400 `notCharged:true` and you are NOT charged. Duplicates are ignored.

Score up to 10 x402 endpoints in a single paid call. Each found result carries the FULL trust report — identical to POST /v1/x402-trust: score, grade, scoreRange, recommendation, confidence breakdown, the component/subscore breakdown, explanations, flags + flagsDetailed, advertised price, and 30-day on-chain stats — not just the scalar verdict. Cache rows older than 15 minutes are recomputed on-demand from the latest stored probes and settlements, so scores typically reflect reality within minutes. No live network re-probe is performed — for a fresh live probe use /v1/x402-trust. Per-request recompute limits apply (time + count); results include `recomputed` and `computed_at` so you can see which rows used cached vs freshly computed scores. Resources not in our observation set return `found:false`; you still pay for the batch AS LONG AS at least one resource is tracked. If NONE of the supplied resources are in our observation set the request is rejected with HTTP 400 `notCharged:true` and you are NOT charged. Duplicates are ignored.

Score up to 200 x402 endpoints in a single paid call. Each found result carries the FULL trust report — identical to POST /v1/x402-trust: score, grade, scoreRange, recommendation, confidence breakdown, the component/subscore breakdown, explanations, flags + flagsDetailed, advertised price, and 30-day on-chain stats — not just the scalar verdict. Cache rows older than 15 minutes are recomputed on-demand from the latest stored probes and settlements, so scores typically reflect reality within minutes. No live network re-probe is performed — for a fresh live probe use /v1/x402-trust. Per-request recompute limits apply (time + count); results include `recomputed` and `computed_at` so you can see which rows used cached vs freshly computed scores. Resources not in our observation set return `found:false`; you still pay for the batch AS LONG AS at least one resource is tracked. If NONE of the supplied resources are in our observation set the request is rejected with HTTP 400 `notCharged:true` and you are NOT charged. Duplicates are ignored.

Score up to 50 x402 endpoints in a single paid call. Each found result carries the FULL trust report — identical to POST /v1/x402-trust: score, grade, scoreRange, recommendation, confidence breakdown, the component/subscore breakdown, explanations, flags + flagsDetailed, advertised price, and 30-day on-chain stats — not just the scalar verdict. Cache rows older than 15 minutes are recomputed on-demand from the latest stored probes and settlements, so scores typically reflect reality within minutes. No live network re-probe is performed — for a fresh live probe use /v1/x402-trust. Per-request recompute limits apply (time + count); results include `recomputed` and `computed_at` so you can see which rows used cached vs freshly computed scores. Resources not in our observation set return `found:false`; you still pay for the batch AS LONG AS at least one resource is tracked. If NONE of the supplied resources are in our observation set the request is rejected with HTTP 400 `notCharged:true` and you are NOT charged. Duplicates are ignored.

Full trade timeline of a Solana meme token: amounts, buy/sell side, wallets. Use to reconstruct who traded what and when

Semantically similar endpoints that currently out-score a given one on the trust score. Each carries score, grade, similarity, advertised price, and endpoint page; same-host siblings and avoid-flagged endpoints are excluded. An empty list means nothing beats the subject.

Crypto market data for AI agents: market capitalization, 24-hour trading volume, 24h percent change, circulating and total supply, and market-cap rank for any coin. Query by Coinpaprika id (btc-bitcoin) or common ticker (btc, eth, sol). One call, USD-denominated, keyless.

Use when an agent needs an ERC-20's basics on Base before quoting, transferring or approving it. Input: address (token contract); optional holder (adds balance and share of supply) and spender (adds allowance, flags unlimited approvals). Output: JSON block+time, name, symbol, decimals, totalSupply raw and decimal, known issuer if curated. Name/symbol are self-reported. EOA or non-ERC-20: 4xx, not charged. Example: ?address=0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913

Monitor one endpoint for 30 days: alerts on payTo, price, asset or network changes, 402-spec regressions, delisting, and liveness. Push to signed HTTPS webhooks or Slack/Discord URLs (max 5 each), all connection-tested before payment. Returns a one-time bearer secret; edit URLs or cancel early via bearer-authed PATCH/DELETE /v1/watch/{id}, or poll the append-only event log.

Score up to 500 x402 endpoints in a single paid call. Each found result carries the FULL trust report — identical to POST /v1/x402-trust: score, grade, scoreRange, recommendation, confidence breakdown, the component/subscore breakdown, explanations, flags + flagsDetailed, advertised price, and 30-day on-chain stats — not just the scalar verdict. Cache rows older than 15 minutes are recomputed on-demand from the latest stored probes and settlements, so scores typically reflect reality within minutes. No live network re-probe is performed — for a fresh live probe use /v1/x402-trust. Per-request recompute limits apply (time + count); results include `recomputed` and `computed_at` so you can see which rows used cached vs freshly computed scores. Resources not in our observation set return `found:false`; you still pay for the batch AS LONG AS at least one resource is tracked. If NONE of the supplied resources are in our observation set the request is rejected with HTTP 400 `notCharged:true` and you are NOT charged. Duplicates are ignored.

For bots that poll: crowd-state events (a perp entering or leaving a state) since a timestamp, newest first, up to 7 days back. Each event is signed with the mark price at the time. Not investment advice.

Routes requests across open-weight models using task fit, tool calling, vision, JSON format, context, output capacity, provider availability, and price. Send POST application/json with model set to ai-open-models/auto and a non-empty messages array. task_type is optional; when omitted, Auto classifies the request. Supports function tools, JSON responses, and mixed text/image messages using public HTTPS image URLs or base64 data URIs. Multipart uploads and streaming are not supported.

Hash a string with SHA-256 and return hex plus a short prefix. Deterministic, no network.

Turn free text into a URL-safe lowercase slug. Deterministic, no network.

Given a company website domain, returns a compact company card: the business name and the page element it came from, a generic role contact address (info@, sales@, support@ ...) only if the site publishes one, never a personal address, and the names of up to 10 technology platforms the site runs. Same scrape and evidence check as /scrape, without the evidence detail, at half the price. Free prompt-injection scan included. Not charged if the page cannot be used or no business name is found.

DeAI artifact gateway: reuse (package_check). Deterministic JSON with byte-exact quotes for $0.0100; no crawl, no bot walls.