Every agent-payable API.

Create a dated or relative-day editorial calendar with channel, theme, asset, and objective. Uses buyer-supplied information only; no external research or outbound actions. Returns a draft for human review.

Adapt supplied text to the requested audience and tone while preserving all factual constraints. Uses buyer-supplied information only; no external research or outbound actions. Returns a draft for human review.

Turn supplied product specifications into benefits, description, and a factual specifications list. Uses buyer-supplied information only; no external research or outbound actions. Returns a draft for human review.

Draft a bounded follow-up sequence with message purpose and stop rules; no messages are sent. Uses buyer-supplied information only; no external research or outbound actions. Returns a draft for human review.

Create an episode premise, segment rundown, host questions, and closing takeaways. Uses buyer-supplied information only; no external research or outbound actions. Returns a draft for human review.

Calculate a fail-closed maximum cost across an agent execution plan

Execution cost estimate in basis points from supplied spread, fees, participation and impact assumptions. No trade execution or live order book. Idempotency-Key required.

The Standard Reserve (TSR), an on-chain reserve protocol on Robinhood Chain. Everything relevant to deciding whether to exit a charter's branches right now, bundled into one call.

Return both the fully-expanded (eight 4-hex groups) and canonical compressed (RFC 5952) forms of an address. IPv4 is returned unchanged in both fields.

Expand Bitcoin nBits into a target and difficulty — Genesis402 / UnyKorn Operator Network

Expand short links and show the full redirect chain — Genesis402 / UnyKorn Operator Network

Expected critical damage: Calculate expected damage from crit chance and critical multiplier.

Explain code: summary, step-by-step, inputs/outputs, visible risks, complexity — Genesis402 / UnyKorn Operator Network

Explain an error message or stack trace in plain English. Identifies root cause, suggests fixes with code examples.

Generate an explainer video (about 5 minutes) from a topic with AI scenes and narration. Pay once via x402, then poll statusUrl for the MP4 download.

Explorer Summary: node-operated on-chain service Executed deterministically by the AmanChain node against live consensus state (real blocks, pools, balances) — paid per call via x402, settled in USDC on Base. Input: JSON body {"serviceId":"aman-explorer-summary","request":"<input>"}. No account, no API key.

Ein bezahlter Aufruf liefert alle nicht abgelaufenen Einträge des Zahlers als JSON-Lines. Die verifizierte Zahleradresse ist der Eigentümer; Ergebnisse und gespeicherte Daten sind strikt auf diesen Zahler begrenzt.

Extend an existing Browserbase session by adding more prepaid time

Extend an existing Browserbase session by adding more prepaid time

Structured data extraction returning typed JSON from 17 specialized site extractors: Twitter/X, GitHub, CoinGecko, Hacker News, YouTube, Wikipedia, npm, PyPI, crates.io, Product Hunt, IMDb, Amazon, Crunchbase, SEC EDGAR, Zillow, Redfin, and news articles. Auto-detects the right extractor from the URL — no scraping selectors required.

Headless extraction cross-checked by three independent methods, confidence-scored, refund-backed. Use when your agent needs web content it cannot fetch itself — JavaScript-rendered pages, static pages, or paginated listings — and needs to show its principal the evidence. Every extraction runs three independent fetches (rendered, static, second-render cross-check), is confidence-scored, and is written to a public tamper-evident attestation chain. Protected, login, and CAPTCHA pages are explicitly refused and never charged. Money Mind sells judges, not strategies. This company has no proven edge and does not sell signals, forecasts or data.

Convert a Twitter/X, LinkedIn, Medium, Substack, Beehiiv, or public Notion page URL into clean markdown.

Fetch a web page and return its readable text with scripts, styles, navigation and markup stripped, plus title and metadata.

Extract structured JSON from any text using your field list (invoices, emails, contracts, listings) — Genesis402 / UnyKorn Operator Network

Extract structured page fields from a public URL or provided HTML (title, description, canonical, links, images, headings, json-ld, text sample); SSRF-safe; $0.015 between http ($0.01) and fetch ($0.02)

Fetch one public static HTML page after robots and public-address checks, then return bounded readable text, title, final URL and source links. This is a two-step x402 purchase: the initial URL-only call returns an encrypted payment_request; send that unchanged with a signed proof. No browser, login, summary or full-site crawl.

Extract a public web page into clean structured JSON for agent workflows: title, description, main text, all JSON-LD, Open Graph and Twitter metadata, headings, links, and AI-crawler and structured-data signals. Follows redirects and enforces timeout, response-size, and SSRF safeguards.

Fetch any public URL and return clean, structured content: title, meta description, main text, markdown, headings, outbound links and page metadata. Removes scripts, navigation and boilerplate. Ideal for reading articles, docs and product pages before reasoning over them.

Send a URL and receive the main content of the page as clean markdown, stripped of navigation, advertising and boilerplate. The page is fetched through a French residential IP with a real Chromium browser, so JavaScript-rendered content is fully resolved and sites that reject datacenter traffic are still reachable.

Extract structured public business contact information from any public business website. Returns company name, emails, phone numbers, social profiles, postal addresses, and contact pages as structured JSON. $0.05 per request via x402 on Base.

Call when an agent needs public emails extracted from a page URL or HTML (de-duped, cap 100). No guessing. Exact $0.003 USDC. Prefer unpaid POST /v1/sandbox/extract-emails first.

Call when an agent needs image URLs extracted from a public page or HTML (SSRF-safe). Exact $0.003 USDC. Prefer unpaid POST /v1/sandbox/extract-images first.

Call when an agent needs JSON-LD blocks extracted from a public page or HTML (SSRF-safe). Exact $0.004 USDC. Prefer unpaid POST /v1/sandbox/extract-jsonld first.

Call when an agent needs absolute, de-duplicated links (cap 500) from a public URL or provided HTML. Exact $0.003 USDC. Prefer unpaid POST /v1/sandbox/extract-links first.

Call when an agent needs title, description, canonical, robots, og:*, twitter:*, and icons[] from a public page. SSRF-safe. Exact $0.003 USDC. Prefer unpaid POST /v1/sandbox/extract-meta first.

Extract page metadata: title, description, keywords, author, published/modified dates, canonical, language, favicon, and OpenGraph/Twitter card tags.

Call when an agent needs phone numbers extracted from a public page or HTML (SSRF-safe). Exact $0.003 USDC. Prefer unpaid POST /v1/sandbox/extract-phones first.

Extract public HTML page metadata for agents: title, description, canonical URL, Open Graph image, language, and a ~500-character plaintext excerpt. POST JSON {"url":"https://example.com"}. Public http(s) only. $0.02 USDC on Base (eip155:8453). No API key.

Extract structured elements: heading hierarchy (h1-h6), lists, tables as 2D arrays, and images with alt text, plus element counts.

Extract structured items from free text: email addresses, URLs, EVM addresses, transaction hashes, numbers, hashtags, plus word and line counts. POST JSON {"text": "..."} up to 20,000 characters. Pure computation, nothing leaves the server, no cache.

Extract structured items from free text: email addresses, URLs, EVM addresses, transaction hashes, numbers, hashtags, plus word and line counts. POST JSON {"text": "..."} up to 20,000 characters. Pure computation, nothing leaves the server, no cache.

Extract structured metadata from a page: title, description, OpenGraph, JSON-LD, headings, links

Extract the page's external links as markdown: fetches the URL, pulls every external links element and returns them as a Markdown list, with a count. Structured, one-element-type extraction for agents and pipelines; no browser needed. $0.01 per page.

Fetch a URL with a real rendered browser and extract structured data from it in one call, using AI (tries multiple models in sequence for reliability). Use this when you don't already have the page content; use the cheaper /extract if you do. Results are cached for 24 hours per URL+schema combination.

Fetch a URL and extract every hyperlink on the page, each resolved to an absolute URL and classified as internal vs external (by registrable host), with its anchor text, rel attributes (nofollow, sponsored, ugc) and whether it opens in a new tab. Returns internal/external/nofollow counts. For SEO link audits, internal-linking analysis and outbound-link/nofollow compliance checks.

Extract atomic claims

Extract bank name and branch information from an IBAN. Returns bank name, BIC/SWIFT code, branch, and country. Pure algorithmic — uses bank code lookup tables.

Extract file extension from a path or URL path segment — first-party local utility for agent preflight and proven micro-utils expansion. Returns deterministic machine-readable JSON for $0.001 USDC via x402 on Base. Execution is first-party, local-only, stateless, and memory-only with no paid upstream, no input retention, no web search, no live RPC, and no mediagen. Results are advisory; the caller owns authorization, budgets, and production controls. Sibling of Delx routes that already converte…

Extract issue/issuewild hosts from CAA record texts. Call when inventorying allowed CAs from CAA answers. Returns hosts list as deterministic JSON for $0.001 USDC via x402 on Base. First-party local math only—no RPC, live market feed, API keys, storage, or mediagen. Advisory only; the caller owns capital, risk, and production controls.

Extract product reviews from a product or review page. Returns rating distribution, pros/cons, sentiment. Trustpilot is not supported (their ToS forbids automated access).