My usage (wallet-keyed purchase

Look up one X (Twitter) account by username: id, display name, bio, account creation date, verification status and type, location, link, protected flag, and public metrics (followers, following, tweet count, listed count).

What's a competitor using? Tech stack, HTTP headers, WHOIS, and page metadata in one call. Competitor scan skill pack: one x402 payment runs 4 underlying tools (tech-stack, http-headers, whois, meta); partial-success per step.

DeFi market overview: total TVL, ETH price, Base gas, and global crypto stats in one call. DeFi dashboard skill pack: one x402 payment runs 4 underlying tools (defi-tvl, crypto-price, gas-snapshot, crypto-global); partial-success per step.

Current yield curve snapshot: full Treasury curve, key spreads, and average rates in one call. Yield dashboard skill pack: one x402 payment runs 3 underlying tools (treasury-yield-curve, yield-curve-spread, treasury-avg-rates); partial-success per step.

Grade a page's content quality - extract the readable content then analyze keyword density. Content grade skill pack: one x402 payment runs 3 underlying tools (extract, keywords, readability-score); partial-success per step.

End-to-end DNS health check: records, multi-resolver propagation, WHOIS, ASN, robots.txt, and reachability. DNS & network ops skill pack: one x402 payment runs 6 underlying tools (dns-lookup, dns-propagation, asn-info, whois, http-check, robots-check); partial-success per step.

Explain what an EVM transaction actually did: confirmation status, the raw transaction from the chain, decoded calldata with typed parameters, the resolved function signature, and labeled counterparties. Transaction forensics skill pack: one x402 payment runs 5 underlying tools (tx-status, evm-rpc, calldata-decode, selector-lookup, address-label); partial-success per step.

Neural (embedding-based) web search over Exa's curated index, which finds pages by meaning rather than keyword overlap. Use it when a keyword engine returns the wrong thing: conceptual questions, 'pages like this one', or niche technical writing. Returns up to 10 results with title, URL, published date and author. Complements the Brave-backed web search rather than replacing it.

Execute Python or JavaScript code in a secure, isolated cloud sandbox (Pro tier). Same as /api/code-run but with 60s timeout and 50k char code limit for longer computations. Returns stdout, stderr, and the expression result.

Metadata, an AI-written summary, and a preview of the opening pages of a PDF - understand what a document says without reading the whole thing. The catalog's first AI-summarization pack, complementary to document-intel's deterministic format extraction (no AI, no summarization there). Document brief skill pack: one x402 payment runs 3 underlying tools (pdf-info, pdf-summarize, pdf-extract-pages);

Pull SEC filings, the latest close, historical prices, and macro context for a single ticker in one pass. Financial research skill pack: one x402 payment runs 6 underlying tools (stock-quote, stock-history, edgar-filings, edgar-company-facts, edgar-insider-trades, fred-series); partial-success per step.

Turn any PDF or image URL into structured data - metadata, extracted text, sliced page ranges, OCR for scanned docs, decoded barcodes / QR codes - without falling back to a vision LLM guess. Built for the messy 30% of documents where pdf-to-markdown alone returns nothing useful. Document intelligence skill pack: one x402 payment runs 7 underlying tools (pdf-info, pdf-to-markdown, pdf-extract-pages

Is this domain legitimate? WHOIS age, DNS resolution, scam/phishing search results, and HTTP headers for a quick trust assessment. Brand protection skill pack: one x402 payment runs 4 underlying tools (whois, dns-lookup, search, http-headers); partial-success per step.

Run read-only SQL against Coinbase's indexed, DECODED blockchain data - base.events (decoded logs with parameters), base.transactions, base.blocks, base.decoded_user_operations, base.transaction_attributions (builder codes), plus solana.instructions and hyperevm.events. ClickHouse-dialect SELECTs, server-side grammar validation, up to 50k rows / 30s / 12 joins. Ask Base anything - token flows, eve

OpenAI-compatible chat completions paid per call in USDC: point any OpenAI SDK at this base URL and send a normal chat request, with the model chosen from a curated list and streaming supported. Use it when an agent needs a model answer without an API key or an account, one call at a time, with a receipt for each.

Comprehensive company research report in one call: latest close, financials, SEC filings, insider trades, and recent news - all in parallel. Company dossier skill pack: one x402 payment runs 5 underlying tools (stock-quote, company-financials, edgar-filings, edgar-insider-trades, search); partial-success per step.

Everything about a cryptocurrency in one call: live price, 90-day history, trending status, global market context, news search, and top article extraction. Crypto dossier skill pack: one x402 payment runs 6 underlying tools (crypto-price, crypto-history, crypto-trending, crypto-global, search, extract); partial-success per step.

Full domain security and SEO intelligence in one call: WHOIS, DNS, TLS cert, HTTP headers, tech stack, robots policy, and certificate transparency. Domain intel skill pack: one x402 payment runs 6 underlying tools (whois, dns-lookup, tls-cert, http-headers, tech-stack, robots-check); partial-success per step.

Execute Python or JavaScript code in a secure, isolated cloud sandbox. Returns stdout, stderr, and the expression result. No setup needed; pay per call via x402. 30s timeout, 10k char code limit.

Generate an image from a text prompt using GPT Image 2 (low quality, 1024x1024). No API key needed; pay per call via x402. Returns base64 PNG. Prompt capped at 1000 chars. A render takes 10 to 30 s; use a client timeout of at least 60 s.

Convert text to speech using OpenAI TTS-1: returns audio (the base64-encoded file in the format asked for: mp3, opus, aac, flac, wav or pcm) with model, voice, format and chars (the characters spoken). 10 voices available. No API key needed; pay per call over x402 or MPP. Text capped at 2000 chars. Model-backed. For high-volume speech where timbre matters less, /api/tts-lite is the same interface

OpenAI-compatible chat completions GROUNDED in a live web search on every call: the gateway runs an Exa search (up to 5 results) for the prompt, hands the results to the model, and returns the answer with url_citation annotations - $0.03 per call in USDC, no API key, no signup. Model is chosen server-side like the auto tier (omit "model" or send "auto"; explicit ranked models accepted); the respon

Quick company snapshot: latest close, 9 key financial metrics (revenue through cash flow), and upcoming earnings - one call, one payment. Financial analysis skill pack: one x402 payment runs 3 underlying tools (stock-quote, company-financials, stock-history); partial-success per step.

Transcribe audio to text using OpenAI (gpt-transcribe). Provide a URL to an audio file (mp3, wav, m4a, etc.) and get back the transcript. No API key needed; pay per call via x402. Max 4 minutes of audio, 25 MB file size; /api/transcribe-pro takes the same model to 10 minutes.

Everything Agent402 knows about one x402 seller origin, in one read: identity and crawl history, the catalog with the provenance of every price (live-402 or manifest, when it was read, whether it is stale or disagrees with the seller's own declaration), advertised wallets against the wallets that were actually paid (own chain evidence, inherited wallets, shared claims), settlement evidence per sou

Should the loop run another iteration? Send the goal, the iteration that just finished (lastOutput, iteration), and optionally maxIterations, a budget { spentUsd, maxUsd }, the history of earlier iterations (up to 20 of { iteration, summary }, oldest first) and constraints; get back decision (continue, stop or escalate), reason, confidence (0 to 1), the checks that produced it (goalMet, budgetExce

Ask typed questions about up to 4 images (PNG or JPEG) and get answers your code can branch on: noul (yes/no probability), choice, score, and box (where something is, as edges from 0 to 1). Name each image, then refer to it as `name` in a question. Preview: built on Jev features its maker labels experimental. Answers come from a model, not deterministic code.

Find up to 4 things in one image: each comes back with whether it is there (a probability) and its box, as edges from 0 to 1. Preview: built on Jev features its maker labels experimental. Answers come from a model, not deterministic code.

OpenAI's Decisions API on its own wire: point an OpenAI SDK's base URL here and client.decisions.create works unchanged, paid per call. Send input (text, or user messages with input_text parts) and questions; get back answers your code can branch on. predicate returns the probability a condition holds; choice returns one of your values with probabilities and confidence; score returns a probability

Read one email the way an agent that triages mail should before acting on it: observations with evidence and offsets, no score and no verdict. Send the raw RFC 5322 message (multipart, base64 and quoted-printable decoded, 1 MB cap) or the parts you already hold (subject, from, replyTo, html, text, links).

Check an email or web page for text a person reading it would not see but an AI reading it would: HTML comments, display:none or hidden elements, white-on-white or off-screen text, zero-width and tag characters, base64 that decodes to a directive, and directives in alt, title, aria-label, data or meta attributes.

Summarize FDA medical device adverse event reports (openFDA MAUDE) for a device name, brand, product code or manufacturer: total matching reports, counts by event type (death, injury, malfunction), the most reported device problems, and the newest reports with date, event type, device, manufacturer, problems and a short excerpt of the event description. Counts cover every matching report; the repo

FDA drug labeling (openFDA SPL) by brand or generic name, or by NDC: boxed warning, indications and usage, dosage and administration, contraindications, and warnings and precautions, with manufacturer, routes, application number, NDCs and the label's effective date. Each section reports its full length and whether it was cut. Newest label first; the answer says how many labels matched. Live FDA da

Look up the FDA National Drug Code directory (openFDA) by NDC or by brand or generic name: product NDC, labeler, dosage form, routes, active ingredients with strengths, marketing category and application number, pharmacologic class, marketing and listing dates, and the package NDCs with their descriptions. The answer says how many products matched. Live FDA data, no key.

Tell whether a public web page changed since you last looked, with nothing stored on this side. One fetch (15 s, 2 MB) takes the text a reader sees (hidden elements, scripts and styles dropped; a CSS selector narrows it to one region), collapses whitespace, strips any ignore entries (a literal substring, or /pattern/ for a regex, for timestamps and counters), and answers a sha256 fingerprint of th

The published facts about an npm package that ships an MCP server, read before running it: resolved version and publish date, package and version age, maintainer count, provenance attestation, install scripts (preinstall, install, postinstall; prepare listed apart), dependency, optional and bundled counts, declared binaries, deprecation, and the GitHub repository the manifest names (one keyless re

Search FDA 510(k) premarket clearances (openFDA) by applicant, three-letter product code, K number or device name: decision and date, clearance type, device class, regulation number, the FDA classification name, medical specialty, and a link to the FDA record. Newest decision first; the answer says how many clearances matched. Live FDA data, no key.

The typed questions of /v1/judge over a document of up to 900 KB (about 262k tokens), in one call. Preview: built on Jev features its maker labels experimental. Answers come from a model, not deterministic code.

Describe a task (or name a slug) and the Smart Order Router resolves the best-matching tool and RUNS it in the same call - flat $0.55 covering any tool listed at $0.5 or less, from THIS host's catalog or any external seller in the open index - x402 sellers, or MPP sellers on Tempo (Agent402 buys the result over x402 or MPP and sells it to you). One payment, one request, result + receipt.

Describe a task (or name a slug) and the Smart Order Router resolves the best-matching tool and RUNS it in the same call - flat $3.30 covering any tool listed at $3 or less, from THIS host's catalog or any external seller in the open index - x402 sellers, or MPP sellers on Tempo (Agent402 buys the result over x402 or MPP and sells it to you). One payment, one request, result + receipt. /api/route

Google's native generateContent wire on the premium tier. Send Gemini's own request shape (contents, systemInstruction, generationConfig, function declarations) and get Gemini's own response shape (candidates, usageMetadata) back. Point a Google GenAI SDK at this gateway and pay per request with USDC, no account. Also answers the Google-shaped path /v1beta/models/<model>:generateContent.

LLM inference proxy (Premium tier) - o3 or o3-mini reasoning models. Supports vision (up to 2 image URLs) and structured output (response_format: json_object or json_schema). No API key needed; pay per call via x402. Input capped at 32k chars, output at 2048 tokens.

OpenAI-compatible chat completions, premium tier: gpt-5, gpt-6 astra, o3 and o4-mini, claude opus, claude fable 5.1 - paid per call in USDC over x402. Same wire format as /v1/chat/completions with the largest caps (85k chars in, 8192 tokens out).

Anthropic Messages API over x402 - point the Anthropic SDK (or Claude Code / the Agent SDK) at base_url https://agent402.tools/v1/premium and pay $0.50 per call in USDC, no API key, no signup. Same models, caps and price as this tier's /chat/completions route; any model here is served through the Messages wire (Claude natively, others translated). Depth: `effort` (low..max) on Claude 4.7+ and Haik

The 'research a question, return an answer with citations' workflow. answer for the AI-synthesized take with citations, search for the canonical SERP, search-news for time-sensitive context, then a deterministic web-fetch + extract pass on the top citations to verify the answer hasn't hallucinated. Five tools, one cited paragraph, every claim traced back to a fetched URL.

Translate a text into a target language and speak the translation, in one paid call. The translation runs on the /v1/chat/completions gateway tier and the speech on /api/tts (tier "standard", $0.140) or /api/tts-hd (tier "hd", $0.260); the price is the sum of the two.

OpenAI Responses API over x402 - point the OpenAI SDK's responses.create() (or the OpenAI Agents SDK) at base_url https://agent402.tools/v1/premium and pay $0.50 per call in USDC, no API key, no signup. Same models, caps and price as this tier's /chat/completions route; any model here is served through the Responses wire.

Look up up to 10 X (Twitter) accounts by username in one call. Returns each found profile with public metrics (followers, following, tweets, listed), verification status and bio, plus the list of usernames X did not resolve.

Generate a higher-quality image from a text prompt using GPT Image 2 (medium quality, 1024x1024). No API key needed; pay per call via x402. Returns base64 PNG. Prompt capped at 2000 chars. A render takes 20 to 45 s; use a client timeout of at least 60 s.

Transcribe audio to text with the gpt-transcribe model - the same model as /api/transcribe with a longer cap. Provide a URL to an audio file and get back the transcript; add diarize:true for speaker labels, word timestamps and a language confidence score (the scribe-v2 model). No API key needed; pay per call via x402. Max 10 minutes of audio, 25 MB file size.