# AgentRXI

> 232 pay-per-call tools for AI agents over x402 (HTTP 402, USDC). No API key, no account: send the request, read the PAYMENT-REQUIRED header, sign the payment, retry. Every tool was tested live before listing (ongoing checks at Status); failed calls are never charged.

Base URL: https://agentrxi.com
MCP server (streamable HTTP, x402-paid tools): https://mcp.agentrxi.com/mcp
A2A agent card: https://agentrxi.com/.well-known/agent-card.json (free concierge that finds the right tool)
OpenAPI: https://agentrxi.com/openapi.json
Discovery: https://agentrxi.com/.well-known/x402
Status: https://agentrxi.com/status
Accepts: USDC/EURC on Base (eip155:8453); USDC on Polygon (eip155:137); USDC on Arbitrum (eip155:42161); USDC on World Chain (eip155:480)
Full version with example calls and input fields: https://agentrxi.com/llms-full.txt

## Endpoints
- POST /v1/search ($0.006): Web search for AI agents. Send a natural-language query, get ranked results with title, url and snippet. Use when you need fresh information from the live web.
- POST /v1/markdown ($0.01): Fetch any public web page with a real headless browser (JavaScript rendered) and return clean Markdown. Use to read articles, docs, product pages or SPAs that a plain fetch cannot render.
- POST /v1/extract ($0.03): Extract structured JSON from any web page. Give a URL plus a JSON schema or a plain-English prompt describing the fields you want; a headless browser renders the page and an LLM fills the schema.
- POST /v1/scrape ($0.01): Scrape text and attributes from a rendered web page using CSS selectors. Returns every match per selector.
- POST /v1/pdf ($0.02): Render a URL or raw HTML to a PDF file with a headless browser. Returns the PDF bytes. Use for invoices, reports, receipts, archiving pages.
- POST /v1/screenshot ($0.02): Full-page PNG screenshot of any public URL rendered by a real browser. Returns PNG bytes.
- POST /v1/llm ($0.005): Pay-per-call LLM chat completion (Llama 3.1 8B, fast), no API key. Send OpenAI-style messages, get the assistant reply. Flat price per request, up to 2k output tokens.
- POST /v1/llm/large ($0.01): Pay-per-call LLM chat completion on Llama 3.3 70B for harder reasoning, no API key. Same OpenAI-style messages body as /v1/llm. Flat price per request, up to 2k output tokens.
- POST /v1/sentiment ($0.002): Sentiment and tone classification for text (positive / negative / neutral with confidence, plus a one-line reason). Batch up to 20 texts per call.
- GET /v1/email/verify ($0.002): Verify an email address: syntax check, domain MX lookup, disposable-domain and role-account flags. Use before sending or storing an address.
- GET /v1/fx ($0.002): Live foreign-exchange rates (ECB reference, 30+ currencies) and conversion. Query base, symbols and an optional amount.
- POST /v1/rpc/:chain ($0.002): JSON-RPC read access to EVM chains (base, ethereum, polygon, arbitrum, optimism) with no API key. Send a standard JSON-RPC body (eth_call, eth_getBalance, eth_blockNumber, eth_getLogs).
- POST /v1/transcribe ($0.02): Speech to text (Whisper large v3 turbo). Send a public audio/video URL or base64 audio (max 20 MB); get the transcript, detected language, timed segments and WebVTT subtitles.
- POST /v1/speak ($0.01): Text to speech. Send up to 2000 characters and a language (en, es, fr, zh, jp, kr); get a natural-sounding WAV recording back.
- POST /v1/translate ($0.003): Translate text between about 100 languages (M2M-100). One text or a batch of up to 20; give target_lang and optionally source_lang (default en).
- POST /v1/summarize ($0.02): Summarize any web page or long text. A headless browser renders the URL, an LLM writes a faithful summary: short (2-3 sentences), medium (one paragraph) or bullets.
- POST /v1/image/generate ($0.02): Generate an image from a text prompt (FLUX.1 schnell). Returns JPEG bytes. Good for thumbnails, social posts, mockups and illustrations.
- POST /v1/image/describe ($0.01): Describe an image and read every piece of visible text in it (vision LLM). Send a public image URL or base64 image; optional custom question. Works for receipts, screenshots, signs and charts.
- POST /v1/embed ($0.002): Text embeddings for semantic search and RAG (BGE-M3, multilingual, 1024 dimensions). Up to 100 texts per call, one flat price.
- GET /v1/weather ($0.002): Current weather and up to 14-day forecast for any place name or lat/lon: temperature, feels-like, humidity, rain chance, wind, sunrise and sunset. Metric or imperial.
- GET /v1/crypto/price ($0.002): Live crypto prices with 24h change and market cap. Pass symbols (btc,eth,sol) or CoinGecko ids, up to 50 coins, in up to 10 currencies (usd,cad,eur...).
- GET /v1/wallet ($0.003): Wallet snapshot on Base or Ethereum: native ETH balance, nonzero balances of the major tokens (USDC, USDT, WETH, DAI, cbBTC, WBTC and more), transaction count and contract flag.
- GET /v1/domain ($0.002): Domain lookup: availability, registrar, created and expiry dates (RDAP/WHOIS), nameservers, A/AAAA/MX/NS/TXT records, and whether the site answers over HTTPS.
- GET /v1/news ($0.005): Latest news headlines matching a query from 12 major outlets (BBC, NPR, Guardian, Al Jazeera, CBC, CNBC, NYT, TechCrunch, Verge, Ars Technica, CoinDesk, ESPN) plus Hacker News. Titles, links, source and time.
- POST /v1/document ($0.01): Document to text: convert PDF, Word (docx), Excel (xlsx/xls), ODS/ODT, CSV, HTML, XML or images to clean Markdown. Send a public file URL or base64 file plus filename (max 25 MB).
- GET /v1/filings ($0.005): US public company filings and fundamentals from SEC EDGAR: latest annual revenue, net income, EPS, assets, liabilities, cash, shares, plus recent 10-K/10-Q/8-K filings with links. Query by ticker or CIK.
- GET /v1/facts ($0.002): Fact lookup for grounding: best-matching Wikipedia article summary plus structured Wikidata facts (website, founding date, birth/death dates, population, coordinates) and the source link. Any language edition.
- GET /v1/papers ($0.003): Academic paper search across 250M+ works (OpenAlex): title, authors, year, venue, DOI, open-access PDF link, citation count and abstract. Sort by relevance, most recent or most cited.
- POST /v1/rerank ($0.002): Rerank up to 100 documents by relevance to a query (BGE reranker). Returns indices and scores, best first. Drop-in step for RAG and search pipelines.
- POST /v1/moderate ($0.002): Safety check (Llama Guard 3): classify up to 10 texts as safe or unsafe with hazard categories (violence, weapons, hate, self-harm, sexual content, privacy, elections and more). Check user input or your own reply before posting.
- GET /v1/ens ($0.002): Crypto name lookup: resolve ENS and Basenames (vitalik.eth, jesse.base.eth) to a wallet address with avatar, url, twitter and description records, or reverse-resolve a 0x address to its primary name.
- GET /v1/gas ($0.002): Live gas prices on Ethereum, Base, Arbitrum, Optimism and Polygon: gas price, next base fee, slow/normal/fast priority tips, and USD cost of a simple transfer.
- POST /v1/sitemap ($0.02): List every page on a website: reads robots.txt and all sitemaps (including sitemap indexes), with last-modified dates; falls back to on-page links. Up to 5000 URLs.
- POST /v1/seo ($0.02): SEO audit of a page: score, list of issues, title and meta description length, canonical, robots, Open Graph, H1/H2 headings, images missing alt text, internal/external links, broken-link check on 25 links, word count and response time.
- GET /v1/holidays ($0.002): Public holidays for 100+ countries (optional state/province), plus business-day math: count business days between two dates, add N business days to a date, or check if a date is a business day.
- GET /v1/token/report ($0.01): Token risk report with a plain-English AI verdict for any token on Base, Ethereum, Polygon, Arbitrum, Optimism or Solana. EVM: honeypot sell simulation, buy/sell tax, verified source, upgradeable proxy, owner, supply, holders, main pool liquidity, price and 24h change, plus a low/medium/high/critical risk rating.
- GET /v1/token/price ($0.002): USD price and 24h change for any token by contract address (up to 30 at once) on Base, Ethereum, Polygon, Arbitrum, Optimism, BSC, Avalanche, Solana or World Chain. Covers long-tail DEX tokens that ticker-based price feeds miss.
- GET /v1/token/chart ($0.003): Price history for any token contract: a time series at 5m to 1w intervals (up to 500 points) with open, close, high, low and percent change. Works for DEX-only tokens.
- GET /v1/defi/yields ($0.003): Best DeFi yields across 16,000+ pools: filter by chain, protocol, token symbol, stablecoin-only and minimum TVL; sort by APY or TVL. Returns APY (base + reward), 30-day mean APY, TVL, IL risk and a link.
- GET /v1/defi/tvl ($0.002): Total value locked for a DeFi protocol (aave, uniswap, aerodrome, lido...) and/or a chain (Base, Ethereum, Solana...), with the chain's TVL rank.
- GET /v1/perps ($0.002): Perpetual futures market data from Hyperliquid: mark and oracle price, 24h change, hourly and annualized funding rate, open interest, 24h volume, premium and max leverage. Pick coins or get the top markets by volume.
- GET /v1/predictions ($0.002): Live prediction market odds from Polymarket: search any topic or get the most-traded markets. Returns each outcome's implied probability, 24h and total volume, liquidity, end date and link.
- GET /v1/nft ($0.003): NFT lookup on Ethereum, Base, Polygon, Arbitrum or Optimism: collection name, symbol, standard and supply; with token_id also the current owner and resolved metadata (name, description, image, attributes) from IPFS/Arweave/HTTP.
- GET /v1/company ($0.01): Company profile from a domain: reads the website and returns name, tagline, description, industry, products, audience, headquarters, founding year and business model, plus contact emails, phone numbers and social profiles (LinkedIn, X, GitHub...).
- GET /v1/geocode ($0.002): Geocode a place, landmark or street address to latitude/longitude with city, region, country, postcode, timezone and population where known. Cities via GeoNames, addresses and points of interest via OpenStreetMap.
- GET /v1/time ($0.002): Trusted current time (or a given moment) in UTC, unix seconds/ms, and up to 20 IANA time zones with local time, weekday and UTC offset. Also converts a timestamp between zones.
- POST /v1/devtools ($0.002): Developer toolbox in one call: sha256/sha1/sha512 hashes, base64/url/hex encode and decode, JWT decode, JSON format/validate, UUIDs, secure random numbers and passwords, regex test, slugify, word count and timestamp conversion.
- GET /v1/fun ($0.002): Something fun on demand: a joke, a true fun fact, a riddle with answer, a famous quote, a trivia question or a piece of life advice.
- GET /v1/ip ($0.002): IP address and ASN lookup from the internet registries (RDAP): network name and range, owning organization, country, origin ASN, abuse contact email, registration dates and reverse DNS. Pass ip= (IPv4/IPv6) or asn=.
- GET /v1/economy ($0.003): Macroeconomic indicators for any country: GDP growth, inflation, unemployment, GDP, GDP per capita, government debt, budget balance, current account and population (IMF World Economic Outlook, including forecasts), plus World Bank interest rates, exports, FDI and more; ECB policy rate for euro countries.
- GET /v1/serp ($0.006): Search engine results page in the familiar SERP shape: organic_results with position, title, link, displayed_link, domain, favicon and snippet, plus total results and top domains. Up to 20 results. For SEO, rank tracking and research agents.
- GET /v1/company/registry ($0.003): Official legal-entity registry lookup (GLEIF Global LEI Index, 200+ jurisdictions): legal name, LEI, active/inactive status, legal form, jurisdiction, company registration number and authority, legal and headquarters address, creation date and direct parent. Search by name (optionally country) or by LEI. For KYB, compliance and due diligence.
- POST /v1/embeddings ($0.002): OpenAI-compatible embeddings endpoint (bge-m3, 1024 dimensions, 100+ languages): same request and response shape as OpenAI /v1/embeddings, including encoding_format base64. Up to 100 inputs per call, flat price, no API key: point any OpenAI SDK at https://agentrxi.com/v1 and pay per request with x402.
- POST /v1/images/generations ($0.01): OpenAI-compatible image generation (FLUX.1 schnell): same shape as OpenAI /v1/images/generations, returns b64_json (or a data URL with response_format=url). One 1024px JPEG per call, flat price, no API key.
- POST /v1/audio/transcriptions ($0.01): OpenAI-compatible speech to text (Whisper large v3 turbo): multipart file upload exactly like OpenAI /v1/audio/transcriptions, with response_format json, text, srt, vtt or verbose_json. Also accepts a public audio url. Up to 20 MB, flat price, no API key.
- POST /v1/audio/speech ($0.005): OpenAI-compatible text to speech (MeloTTS): same request shape as OpenAI /v1/audio/speech (input, voice, model); returns a WAV file. Languages en, es, fr, zh, jp, kr via language. Up to 2000 characters, flat price, no API key.
- POST /v1/moderations ($0.002): OpenAI-compatible moderation (Llama Guard 3): same response shape as OpenAI /v1/moderations with flagged, categories and category_scores, plus the raw Llama Guard codes. Up to 10 inputs per call.
- GET /v1/token/solana ($0.01): Solana token risk report (rug check) for any SPL or Token-2022 mint: mint and freeze authority, top-holder and developer concentration, serial-launcher check, Jupiter suspicious flag, liquidity, pool age, organic trading score, holders, price and market cap, a low/medium/high/critical rating and a plain-English AI verdict.
- GET /v1/token/verdict ($0.005): Quick AI token verdict: a 2-3 sentence plain-English risk summary plus risk level and red flags for any token on Base, Ethereum, Polygon, Arbitrum, Optimism or Solana. Built on honeypot sell simulation and tax checks (EVM) or mint/freeze authority and holder concentration (Solana). Half the price of the full report.
- GET /v1/token/scan ($0.02): Batch token risk scan: up to 5 tokens in one call, any mix of Base, Ethereum, Polygon, Arbitrum, Optimism and Solana. Each gets a risk rating, red flags, price and liquidity; the riskiest one is named. For screening a watchlist, a wallet's holdings or a list of new launches.
- GET /v1/answer ($0.02): Cited answers: ask a question, get a concise answer written from live web pages with numbered [n] citations and the source list. Searches the web, reads the top pages and writes only from what they say (gpt-oss-120b).
- GET /v1/research ($0.10): Deep research report: plans several searches, reads up to 8 sources and writes a structured Markdown report (summary, key findings, details, open questions, numbered sources) with inline citations. Takes 20 to 60 seconds.
- POST /v1/ask ($0.02): Ask a document: give a web page, PDF, Word, Excel or CSV URL (or raw text) and a question; get an answer backed by exact quotes from the document. Long documents are searched with embeddings first.
- POST /v1/chunk ($0.01): Ready-to-search chunks: turns a URL (page, PDF, Office file) or text into clean overlapping chunks with character offsets and bge-m3 embeddings (1024 dims) in one call, ready for any vector store. Up to 300 chunks.
- POST /v1/memory ($0.002): Agent memory: save, get, search, list and delete notes that persist between sessions, private to the wallet that pays. Up to 2,000 keys per wallet, 16,000 characters per value. Pay with an EVM wallet.
- POST /v1/files ($0.01): File hosting: upload a file (text, base64 or copy from a URL) and get a public link that lasts up to 7 days. Images, PDF, text, Markdown, CSV, JSON and audio up to 1 MB. Served safely sandboxed.
- POST /v1/inbox ($0.005): Webhook inbox: create an inbox and get a public URL any service can POST to (free to send), then read the received messages with your token. Keeps 200 messages, 64 KB each, for 7 days.
- POST /v1/schedule ($0.005): Scheduled callbacks: have any https URL called at a set time (1 minute to 30 days ahead, fired within a few minutes of it) with your method, headers and body, so an agent can wake itself up later. Retries up to 3 times; check status with the id.
- GET /v1/watch ($0.005): Page change watch: reports what changed on a web page since your last check (lines added and removed). The first call saves a snapshot; each later call compares and updates it. Snapshots are private to the paying wallet.
- GET /v1/sanctions ($0.005): Sanctions screening for crypto addresses against the US Treasury OFAC SDN list (Bitcoin, Ethereum and EVM chains, Tron, Solana, Monero, XRP, Litecoin and more). Up to 20 addresses per call. Check before your agent sends money.
- GET /v1/link ($0.003): Link safety check: is this URL malware or phishing? Checks Cloudflare's security DNS blocklist, domain age, look-alike and brand-impersonation tricks, shorteners and the redirect chain, then gives a verdict and risk score.
- GET /v1/vulns ($0.003): Package vulnerability check for coding agents: known CVEs/GHSAs for an npm, PyPI, Go, Maven, crates.io, RubyGems, NuGet or Packagist package version, with severity, fixed versions and the latest release (OSV.dev).
- GET /v1/x402/find ($0.002): x402 service finder: describe what you need and get matching pay-per-call x402 services from the Coinbase Bazaar directory, cheapest first, with price, networks and 30-day payer counts.
- GET /v1/x402/check ($0.005): x402 endpoint checker: tests any paid x402 URL for a correct 402, price and networks, pay-to address, discovery metadata, CORS, response time and Coinbase's validator, and lists every issue to fix.
- GET /v1/places ($0.005): Places search: find businesses and points of interest (cafes, pharmacies, hotels, ATMs, restaurants...) near a city, address or coordinates from OpenStreetMap, with category, address, coordinates and distance.
- POST /v1/calc ($0.002): Exact calculator for agents: math expressions (functions, powers, factorials), unit conversion (length, mass, volume, area, time, speed, data, energy, pressure, power, temperature) and date arithmetic (add, diff with business days, weekday).
- POST /v1/convert ($0.002): Data conversion and checking: convert between CSV, TSV, JSON, XML and YAML (typed CSV values), and optionally validate the data against a JSON Schema with a list of every error. Up to 1 MB.
- POST /v1/qr ($0.002): QR codes: make a QR code (PNG or SVG, any size, error-correction level) from text or a URL, or read the text from a QR code in a PNG or JPEG image.
- GET /v1/phone ($0.002): Phone number check: validates a number and returns its country, line type (mobile, fixed line, toll free, VoIP...) and E.164, international and national formats, from Google's libphonenumber data.
- GET /v1/legal ($0.005): US court cases and federal regulations: searches court opinions (CourtListener) and Federal Register rules, proposed rules and notices, with case names, courts, dates, citations, agencies and links.
- POST /v1/office ($0.01): Make office files: an Excel spreadsheet (or CSV) from JSON rows or CSV text, or a Word document from Markdown (headings, bullets, bold, tables). Returns the file as base64, ready to save or attach.
- POST /v1/sql ($0.003): Run SQL on your data: load JSON rows or CSV (or several named tables) into SQLite and run any SELECT, including GROUP BY, JOIN, window functions and CTEs. Up to 100,000 rows.
- POST /v1/image/edit ($0.003): Image tools: resize (fit inside a box), crop, rotate, grayscale and convert or compress PNG and JPEG images from a URL or base64. Up to 16 megapixels.
- GET /v1/domain/audit ($0.005): Domain and email security audit: SPF, DMARC, DKIM, MX, DNSSEC, CAA, HTTPS, HSTS, security headers and HTTP-to-HTTPS redirect, with a grade and the fixes to make.
- GET /v1/techstack ($0.005): Tech stack detection: what a website is built with (CMS, frameworks, e-commerce, analytics, ads, chat, payments, CDN, hosting, server) with the evidence for each.
- GET /v1/wayback ($0.005): Web archive: the Internet Archive snapshot of a page closest to a date, with the archived page text and a list of recent snapshots. See what a page said before it changed.
- POST /v1/timestamp ($0.01): Proof of existence: anchor the SHA-256 of any text, file or URL in the Bitcoin blockchain through OpenTimestamps calendars and get the .ots proof file, so anyone can later verify the data existed at that time.
- GET /v1/random ($0.002): Verifiable random numbers from the drand public beacon (League of Entropy): numbers in a range, or a fair shuffle and pick of your items, with the beacon round so anyone can re-check the result.
- GET /v1/cite ($0.002): Citation formatter: a ready reference in APA, MLA, Chicago, Harvard, IEEE, Vancouver or BibTeX from a DOI, an ISBN or any web page URL.
- GET /v1/hazards ($0.003): Hazard alerts near a place: recent earthquakes (USGS), active US National Weather Service alerts and global disasters (cyclones, floods, wildfires, volcanoes, droughts from GDACS) with distances.
- GET /v1/drug ($0.005): Drug information from openFDA: label (indications, boxed warning, warnings, interactions, dosage), the most reported side effects and recent recalls for a brand or generic drug name.
- GET /v1/trials ($0.005): Clinical trials search (ClinicalTrials.gov): studies for a condition, drug or keyword with status, phase, sponsor, interventions, enrollment and links. Filter by status and location.
- GET /v1/contracts ($0.005): US federal contract awards (FPDS): who won government contracts for a keyword, vendor or agency, with amounts, agency, NAICS code, dates and descriptions.
- GET /v1/jobboard ($0.005): Job postings: every open role at a company (from its Greenhouse, Lever or Ashby board), or remote jobs matching keywords, with titles, locations and links. Useful for sales signals and recruiting.
- GET /v1/vat ($0.003): EU VAT number check against the official VIES register (valid, company name and address), plus IBAN checksum and BIC/SWIFT format validation. Check a supplier before paying an invoice.
- POST /v1/meeting ($0.002): Meeting planner: finds times that fall inside everyone's working hours across time zones over the next days, shows each person's local time, and returns a calendar invite (.ics) for the first slot.
- GET /v1/github ($0.005): GitHub repository report: stars, forks, issues, license, language, activity, latest releases, recent commits and security advisories for any public repo.
- GET /v1/nutrition ($0.003): Nutrition facts (USDA FoodData Central): calories, protein, fat, carbs, fiber, sugar, sodium and key minerals for foods and branded products.
- GET /v1/demographics ($0.003): US demographics by ZIP code (Census ACS 5-year): population, median household income, median age, home value, rent, education, unemployment and poverty.
- POST /v1/errorfix ($0.01): Error fixer for coding agents: paste an error message or stack trace (plus optional code) and get the likely cause and a concrete fix with code, researched from live sources (Stack Overflow, GitHub issues, docs) with citations.
- GET /v1/libdocs ($0.02): Current library docs for agents with stale training: the latest version of an npm or PyPI package, how to use it now, and the breaking changes since the version you know, from its README and changelog.
- GET /v1/since ($0.03): Since-my-cutoff briefing: everything that happened on a topic after a given date (for models whose knowledge stops there), newest first with dates and citations, plus what changed versus the old state.
- POST /v1/mailbox ($0.002): Agent mailbox: send a message to any AI agent by its wallet address and read your own inbox. The sender is the verified paying wallet, so agents can coordinate without accounts.
- POST /v1/tasks ($0.002): Agent task list: add, list, complete and delete tasks that persist between sessions, with due dates and an optional reminder callback to your URL when a task is due. Private to the paying wallet.
- POST /v1/second-opinion ($0.02): Second opinion: three different AI models (gpt-oss-120b, Llama 3.3 70B, Gemma 4) answer independently, then you get the consensus, the points they disagree on, a confidence level and a combined best answer.
- GET /v1/answer/cached ($0.005): Shared answer cache: a recent cited answer to a question similar to yours (from /v1/answer) for a quarter of the price. Not charged when nothing close enough is cached.
- POST /v1/citecheck ($0.01): Citation checker: for each claim and the URL cited for it, reads the source and says whether it really supports the claim (supported, partial, not supported, contradicted) with the deciding quote.
- GET /v1/plan ($0.01): Tool plan with cost: breaks a goal into steps and finds the cheapest paid API for each step (this marketplace and the whole x402 directory), with the estimated total cost before you spend anything.
- GET /v1/jobs ($0.002): Background jobs: result of a slow tool run with async=true (answer, research, ask, errorfix, libdocs, since, second-opinion, bulk read). Results are also POSTed to your webhook_url for free.
- GET /v1/page/actions ($0.005): Page action map for browser automation: every form (fields, labels, required flags), button and link on a page with ready CSS selectors, so an agent can plan clicks and form fills before opening a browser.
- POST /v1/profile ($0.01): Agent profile hosting: publish a public profile page and an A2A agent card for your agent at agentrxi.com/agents/<name>, owned by your wallet. Update it any time.
- POST /v1/chart ($0.005): Chart images: bar, line, pie or scatter charts as PNG or SVG from your numbers, with title, labels, several series and legend. Ready to drop into a report or message.
- POST /v1/pdf/fill ($0.01): PDF forms: list the fillable fields of any PDF, fill them (text, checkboxes, dropdowns) and optionally flatten, or merge up to 10 PDFs into one. Returns the finished PDF as base64.
- POST /v1/grade ($0.01): Answer grader: scores a draft answer 0-10 against the question, a rubric and/or source URLs, lists factual errors and unsupported claims with fixes, and returns an improved answer. A self-check before an agent ships.
- GET /v1/spend ($0.005): Wallet spend report: an agent wallet's outgoing USDC payments on Base, grouped by recipient and matched to x402 sellers, with totals for the period.
- POST /v1/read/bulk ($0.02): Bulk reader: up to 20 web pages read and cleaned to text in one call (instead of 20 separate calls), each trimmed to your character limit. Unreadable pages are flagged, not failed.
- POST /v1/cluster ($0.01): Cluster and label: groups up to 500 texts (reviews, tickets, survey answers, search results) into topics with an AI-written label, size, share and examples for each group.
- POST /v1/context ($0.005): Context packer: from long texts or URLs, picks the passages most relevant to your question and packs them into your token budget, with source markers. Fit more useful context into a prompt for less.
- POST /v1/team ($0.002): Team memory: shared notes for a group of agents. Create a team to get a team id and secret code; any agent with the code can save, get, list, search and delete entries. Up to 5,000 keys per team.
- GET /v1/wallet/portfolio ($0.005): Multi-chain wallet portfolio: every token a wallet holds on Ethereum, Base, Arbitrum, Optimism and Polygon (or Solana) with live USD prices, value per token and per chain, and the total. Spam tokens without a price are filtered out.
- GET /v1/wallet/nfts ($0.005): NFT holdings for any wallet on Base, Ethereum, Arbitrum, Optimism or Polygon, grouped by collection with counts, a sample item and image, OpenSea floor price and an estimated floor value. Spam NFTs are excluded.
- POST /v1/wallet/watch ($0.02): Wallet activity alerts: watch any wallet on Base, Ethereum, Arbitrum, Optimism or Polygon for 7 days; every incoming or outgoing transfer (ETH, tokens, NFTs) is POSTed to your webhook URL within about 10 minutes. Check status with the watch id.
- GET /v1/fec ($0.005): US campaign finance from the FEC: candidates and committees matching a name with party, office, state, status and their latest totals (money raised, spent, cash on hand, individual contributions), with links.
- GET /v1/congress ($0.005): US Congress bills: search bill text by keywords (GovInfo), or pass a bill id such as hr1-119 for its title, sponsor, cosponsors, policy area, latest action and recent actions (Congress.gov).
- GET /v1/evcharging ($0.005): EV charging stations (and other alternative fuel stations) near a place in the US and Canada: network, Level 2 and DC fast port counts, connector types, access hours, pricing, address and distance, from the US DOE station locator.
- GET /v1/solar ($0.005): Solar potential for any address or coordinates: yearly and monthly output of a rooftop system (NREL PVWatts), sun hours, capacity factor, plus estimated yearly savings, install cost and simple payback years.
- GET /v1/college ($0.005): US college facts from the Department of Education College Scorecard: admission rate, tuition, average net price, graduation and retention rates, median earnings 10 years after entry and median debt.
- GET /v1/vin ($0.003): Car VIN check: decodes any VIN (year, make, model, trim, engine, drive, plant) and adds the model year's safety recalls, complaint counts by component and NHTSA crash-test ratings.
- GET /v1/password/check ($0.002): Breached password check: is this password in known data breaches, and how often? Send only the SHA-1 hash (never the password); just the first 5 characters reach Have I Been Pwned (k-anonymity). Up to 50 hashes per call.
- GET /v1/barcode ($0.002): Product barcode lookup (Open Food Facts): name, brand, ingredients, allergens and traces, Nutri-Score, NOVA processing group, eco-score and nutrition per 100 g for packaged food from its EAN/UPC barcode.
- GET /v1/aviation ($0.002): Aviation weather for airports: latest METAR decoded (flight category VFR/IFR, wind, gusts, visibility, ceiling, clouds, temperature, altimeter) plus the TAF forecast, for up to 10 ICAO airport codes.
- GET /v1/satellite ($0.005): Satellite image of any place on any date from NASA (daily true-color MODIS or VIIRS, or night lights), centered on a place or coordinates with your choice of area size. Good for storms, smoke, fires, snow and floods.
- GET /v1/solana/history ($0.005): Solana wallet history in plain language: recent transactions decoded into readable descriptions (swaps, transfers, NFT sales and mints, staking) with the SOL and token amounts in and out, counterparties, fees and explorer links. Filter by type.
- GET /v1/uk/company ($0.005): UK company records from Companies House: status, type, incorporation date, registered address, SIC codes, overdue accounts, insolvency and charges flags, current officers, persons with significant control (owners) and recent filings. Search by name or company number.
- GET /v1/labor ($0.003): US labor and price statistics from the Bureau of Labor Statistics: CPI and core CPI, unemployment, payrolls, average hourly earnings, PPI, participation and job openings (or any BLS series id), with 12-month change.
- GET /v1/energy ($0.003): US energy prices from the EIA: retail gasoline and diesel, WTI crude, Henry Hub natural gas, crude oil inventories and residential electricity prices by state, with the latest value and change.
- GET /v1/airquality ($0.003): Air quality near any place from nearby monitoring stations (OpenAQ): PM2.5, PM10, ozone, NO2 and more, with a US AQI and health category.
- GET /v1/airquality/history ($0.003): Air pollution history for any place: daily average, min and max of PM2.5 (or PM10, ozone, NO2, SO2, CO) from the nearest active monitor for up to 365 days, with daily US AQI, worst day, days over the WHO guideline and an improving/worsening trend.
- GET /v1/airquality/compare ($0.005): Compare current air quality across 2-8 cities: US AQI, category, PM2.5, PM10, ozone and NO2 from the nearest active monitors, ranked cleanest to most polluted.
- GET /v1/airquality/stations ($0.002): Find air quality monitoring stations that are reporting now, near a place or across a country: name, operator, reference-grade flag, coordinates, distance, pollutants measured and last reading time.
- GET /v1/uk/officer ($0.005): Look up a person in the UK company register: matching company officers with birth month/year, then every directorship and secretary role of the chosen match (company, status, role, appointed and resigned dates).
- GET /v1/uk/companies/search ($0.005): Search UK companies by filters for lead lists and market maps: name contains, town or postcode area, SIC industry codes, incorporation date range (or new in the last N days), status and company type. Returns number, name, address, SIC codes and dates.
- GET /v1/uk/filings ($0.004): UK company filing history with direct PDF links to each document (accounts, confirmation statements, officer changes), plus secured charges (lenders, outstanding or satisfied) and any insolvency cases. Filter by category.
- GET /v1/uk/disqualified ($0.004): Search the UK register of disqualified company directors by name: birth date, address, disqualification periods, reasons, the act used and the companies involved.
- GET /v1/uk/kyb ($0.02): UK business verification (KYB) risk check in one call: company status and age, overdue accounts or confirmation statement, insolvency history, disputed or undeliverable office, owners (PSC), outstanding charges, and each current director screened against the disqualified directors register. Returns a 0-100 risk score, level and flags.
- GET /v1/inflation/calculator ($0.002): US inflation calculator from official CPI-U: what an amount of dollars in one year (or month) is worth in another, from 1913 to now, with cumulative and average annual inflation.
- GET /v1/inflation/breakdown ($0.003): What is driving US inflation: 12-month and 1-month CPI change for 20 categories (groceries, restaurants, gasoline, electricity, rent, shelter, used cars, car insurance, airline fares, medical care and more), ranked fastest rising.
- GET /v1/labor/state ($0.003): US unemployment by state: one state's rate, labor force, employed and unemployed with 13 months of history, or all 50 states plus DC ranked lowest to highest.
- GET /v1/wages ($0.004): Salary data for any job title: employment, mean and median annual and hourly pay, and 10th to 90th percentile annual pay, nationally and for a US state, from the BLS occupational wage survey. Job titles are matched to SOC codes automatically.
- GET /v1/energy/forecast ($0.003): Official US energy price forecast (EIA Short-Term Energy Outlook): monthly gasoline, diesel, WTI and Brent crude, Henry Hub natural gas and residential electricity prices for the next 12-24 months, with the latest actual and the 12-month change.
- GET /v1/energy/mix ($0.003): Electricity generation mix for any US state or the whole US: gigawatt-hours and share by fuel (natural gas, coal, nuclear, wind, solar, hydro and more), renewable and carbon-free share, compared with five years earlier.
- GET /v1/energy/gas-prices ($0.002): This week's gasoline or diesel prices across the US: national average, PADD regions, 9 states and 10 metro areas (Los Angeles, San Francisco, Seattle, New York, Chicago, Houston, Miami...), ranked with weekly change.
- GET /v1/energy/electricity-prices ($0.002): Electricity prices for every US state for the latest month (residential, commercial, industrial or all sectors) in cents per kWh, ranked cheapest first with 12-month change and the US average.
- GET /v1/solana/wallet ($0.004): Solana wallet balances in one call: SOL and every SPL token with USD price and value, total portfolio value, plus NFT and compressed NFT counts.
- GET /v1/solana/nfts ($0.003): NFTs owned by a Solana wallet, including compressed NFTs: name, image, collection and grouping by collection, with likely spam airdrops hidden.
- GET /v1/solana/asset ($0.002): Metadata for any Solana token mint or NFT: name, symbol, image, description, supply, decimals, price and market cap, mint and freeze authority (can more be minted? can accounts be frozen?), owner, royalties and creators.
- GET /v1/solana/priority-fee ($0.002): Live Solana priority fee estimate for the accounts or programs your transaction touches: recommended micro-lamports per compute unit, all levels from min to very high, and the total fee in SOL for your compute budget.
- GET /v1/nft/floor ($0.003): Floor price for any Ethereum NFT collection on OpenSea and LooksRare, with the collection name, supply, standard, description, image and social links.
- GET /v1/github/search ($0.003): Find the best GitHub repositories for anything: keyword search with language, topic, minimum stars, created or pushed after filters, sorted by stars or recent activity; returns stars, forks, license, topics and last push.
- GET /v1/github/code ($0.004): Search code across all public GitHub repositories: find real usage examples of a function, API or config key, with file paths, links and the matching code fragments. Filter by language, repo, org or filename.
- GET /v1/github/issues ($0.004): Has anyone hit this error? Searches GitHub issues for an error message (exact phrase first, then keywords): title, repo, open or closed, comments, labels, link and an excerpt, most-discussed first.
- POST /v1/nutrition/recipe ($0.01): Nutrition facts for a whole recipe: give ingredients with household amounts (cups, tbsp, grams, pieces) and servings; returns calories, protein, fat, saturated fat, carbs, fiber, sugar, sodium, cholesterol and potassium per serving and in total, macro split and the USDA match for each ingredient.
- GET /v1/fred/series ($0.002): Any public-domain FRED economic time series by id (UNRATE, CPIAUCSL, GDP, DGS10, thousands more): observations with optional transforms (change, % change, % change from a year ago), frequency aggregation and date range, plus title, units and notes.
- GET /v1/fred/search ($0.002): Search 800,000+ FRED economic series by keywords, most popular first: id, title, frequency, units, seasonal adjustment, date range and whether the series can be served (copyrighted series are flagged).
- GET /v1/rates ($0.003): US interest rates now: fed funds, SOFR, prime rate, 3-month bill, 2, 10 and 30-year Treasury yields and the 10y-2y and 10y-3m spreads, with change over 1 month and 1 year and whether the yield curve is inverted.
- GET /v1/recession ($0.004): US recession dashboard: yield-curve inversions (10y-3m and 10y-2y), real-time Sahm rule, smoothed recession probability, Chicago Fed financial conditions and the unemployment rise from its low, each with whether it is flashing, plus an overall verdict.
- GET /v1/macro/us ($0.004): US economy snapshot in one call: real GDP growth, CPI and core PCE inflation, unemployment, payroll change, retail sales, industrial production, housing starts, M2, fed funds, 10-year yield, WTI oil and the euro exchange rate, each with the previous value.
- GET /v1/route ($0.004): Directions between places (addresses, names or lat,lon) with optional stops: distance in km and miles, travel time, and turn-by-turn steps for driving, trucks, cycling, walking or transit, avoiding tolls, highways or ferries; optional GeoJSON route line.
- GET /v1/isochrone ($0.004): Reachable area from a place within N minutes (or km) by car, truck, bike, walking or transit, up to 3 ranges at once: GeoJSON polygons with area in km². For delivery zones, catchment areas and commute searches.
- GET /v1/route/matrix ($0.006): Travel time and distance matrix between up to 50 origin-destination pairs (places or lat,lon) by car, truck, bike or foot, with the closest pair. For dispatching, store finders and delivery planning.
- GET /v1/map/static ($0.003): Static map image (JPEG) of a place or up to 15 numbered markers, in 7 styles and any size up to 1600 px, returned as base64 and a data URL ready for reports, emails and chat.
- GET /v1/address/verify ($0.003): Address verification and standardization worldwide: parsed components (house number, street, city, state, postcode, country), confidence to building, street or city level, a plain verdict, coordinates, timezone and alternatives.
- GET /v1/demographics/area ($0.005): Demographics for any US address or place at neighborhood (census tract), city, county, state and national level in one call: population, median age, households, median household and per-capita income, home value, rent, homeownership, college degree share, poverty and unemployment.
- GET /v1/business/counts ($0.004): How many businesses of a kind are in a US county, state or ZIP: establishments, employees, annual payroll and average pay by industry (keyword or NAICS code), plus businesses per 10,000 residents for market sizing and competition checks.
- GET /v1/trade ($0.004): US imports and exports from official Census trade data: by product (HS code) the top partner countries with value, share and year-to-date; by country the trade balance and top products; or US totals, for the latest month or any month.
- POST /v1/code/run ($0.02): Run Python 3.13 (numpy, pandas), JavaScript (Node 24) or bash in a fresh isolated container with no Internet access, and get stdout, stderr and the exit code. For calculations, data wrangling, parsing and testing snippets. $0.005 for a 10 s limit, $0.01 up to 30 s, $0.02 up to 60 s.
- POST /v1/firewall ($0.006): Agent Firewall: check untrusted text, HTML or a URL for prompt injection before your model reads it. Finds hidden text, invisible Unicode and ASCII smuggling, role spoofing, instructions aimed at AI, secret or data exfiltration, payment hijacks and tool-call injection; returns a risk score, findings and a sanitized copy. $0.003 per text check, $0.005 per URL.
- GET /v1/kya ($0.01): Know Your Agent: trust check on an agent's wallet before you transact with it. x402 payment history matched against every seller in Coinbase's x402 directory (payments, USDC spent, sellers, last payment), wallet age, smart wallet or key, balances, OFAC sanctions screen, listed seller status, and a risk score with a plain verdict.
- POST /v1/browser/start ($0.03): Rent a real Chrome browser for up to 60 minutes: opens a live session (optionally at a URL) and returns a session id, a screenshot, the page text and the clickable controls. Drive it step by step with /v1/browser/act (click, type, press, scroll, select, go back). The session stays open 10 minutes after each action.
- POST /v1/browser/act ($0.003): Act in your rented browser session: up to 10 steps per call (goto, click by selector, visible text or x/y, type, press a key, scroll, select, wait, back, close). Returns what happened, a fresh screenshot, the page text and the clickable controls.
- GET /v1/crawl ($0.025): Crawl a website into clean Markdown: follows same-site links from a start page (optionally under a path prefix), up to 100 pages, respecting robots.txt. Returns each page's URL, title and text. $0.005 + $0.001 per page. Add store=true (+$0.001) to get a 7-day share link instead of the data inline.
- GET /v1/docs/ask ($0.05): Ask any website or documentation a question: the site is crawled (up to 50 pages), indexed for 7 days and searched; the answer cites the pages it used. Later questions about the same site reuse the index. $0.03, or $0.05 above 25 pages.
- GET /v1/transcribe/pro ($0.06): Premium transcription with Deepgram Nova-3: smart punctuation and formatting, language detection, optional speaker labels (diarization) and word timestamps, for a public audio or video file. $0.012 per audio minute (set max_minutes), minimum $0.02. Add store=true (+$0.001) to get a 7-day share link instead of the data inline.
- GET /v1/speak/pro ($0.06): Premium natural speech with Deepgram Aura-2: 40 English voices (luna, orion, athena, zeus...) and Spanish, returned as MP3 (or base64 JSON). $0.06 per 1,000 characters, minimum $0.005. Add store=true (+$0.001) to get a 7-day share link instead of the data inline.
- GET /v1/image/pro ($0.08): Premium image generation: FLUX.2 dev (highest quality), FLUX.2 klein 9B or 4B (fast), Leonardo Lucid Origin (photoreal, good text in images) or Leonardo Phoenix. Up to 1536 px per side. Priced per image by model, size and steps (about $0.006 to $0.08). Add store=true (+$0.001) to get a 7-day share link instead of the data inline.
- POST /v1/image/inpaint ($0.011): Edit part of an image: send the image and a mask (white = area to repaint) with a prompt, and get the edited image back. Remove objects, replace backgrounds or add items. Add store=true (+$0.001) to get a 7-day share link instead of the data inline.
- POST /v1/storage ($0.01): File storage for agents on R2 with share links. Upload (base64, text or copy from a URL, up to 95 MB; up to 5 GB with upload_large), renew, get, list or delete. Priced by size and time: $0.002 per started 10 MB per week (above 100 MB $0.05 per GB-week); scratch files kept 1-24 hours from $0.002. Downloads are free. Files are private to the paying wallet.
- POST /v1/db ($0.002): Your own private SQLite database that persists between calls, keyed to the paying wallet: create tables, insert, update and query with up to 20 SQL statements per call (parameters supported). Up to 200 MB per wallet.
- POST /v1/vectors ($0.003): Private long-term vector memory for an agent: upsert up to 100 texts with metadata (we embed them, multilingual), then search by meaning. Keyed to the paying wallet. $0.003 per upsert batch, $0.002 per query or delete.
- POST /v1/media/info ($0.003): Inspect any audio or video file with ffprobe: container, duration, bit rate, and every stream's codec, resolution, frame rate, sample rate, channels and language. Up to 20 MB by URL or base64.
- POST /v1/media/convert ($0.02): Convert audio or video between formats with ffmpeg: mp4, webm, mov, mkv, mp3, wav, ogg, opus, m4a, aac, flac. Optional width, fps, crf, audio_bitrate, sample_rate and channels. Up to 20 MB in, 150 s of processing.
- POST /v1/media/trim ($0.01): Cut a clip out of an audio or video file: give start and end (seconds or hh:mm:ss) or duration. mode=precise re-encodes for frame-exact cuts (default); mode=fast copies streams instantly but cuts on keyframes.
- POST /v1/media/thumbnail ($0.005): Grab still frames from a video: one frame at a given time, or up to 10 evenly spaced frames for a storyboard. JPEG, PNG or WebP, width 64-1920 px.
- POST /v1/media/gif ($0.015): Turn a video clip into a palette-optimised animated GIF: start, duration (up to 15 s), fps (4-20) and width (100-800 px).
- POST /v1/media/extract-audio ($0.01): Pull the audio track out of a video as mp3 (default), wav, m4a, aac, flac, ogg or opus, ready for transcription or editing.
- POST /v1/ocr ($0.064): Read the text in a scanned image or PDF with Tesseract (English, French, Spanish, German). PDFs with a text layer are read directly; scanned pages are OCR'd at 300 dpi. $0.006 for one page or image, +$0.002 per extra page (max_pages up to 30; default 5 for .pdf URLs).
- POST /v1/office/convert ($0.015): Convert office documents with LibreOffice: Word, Excel, PowerPoint, OpenDocument, RTF, HTML, CSV or text to PDF (default), or between formats (docx, odt, rtf, txt, html, xlsx, ods, csv, pptx, odp).
- POST /v1/pdf/to-images ($0.055): Render PDF pages to PNG or JPEG at 50-300 dpi (for vision models, previews or thumbnails). $0.005 + $0.001 per page (max_pages up to 50, default 10); continue with first_page.
- POST /v1/barcode/read ($0.003): Read every barcode and QR code in an image: QR, EAN-13/8, UPC-A/E, Code 128/39/93, Codabar, ITF, DataBar and PDF417, with the symbology and decoded text.
- POST /v1/zip ($0.004): Zip up to 20 files (by URL or base64, 20 MB total) into one archive, or list / extract a zip (up to 50 files, 20 MB expanded) so an agent can read what is inside.
- POST /v1/image/convert ($0.004): Convert and resize images with ImageMagick: HEIC/AVIF/PNG/JPEG/WebP/GIF/TIFF/BMP in; PNG, JPEG, WebP, GIF, TIFF, BMP, ICO or AVIF out. Resize (contain, cover or fill), rotate, grayscale, quality, strip metadata; auto-orients phone photos.
- POST /v1/image/diff ($0.004): Compare two images pixel by pixel (visual regression testing for screenshots): count and percent of differing pixels with a fuzz tolerance, plus a diff image with the changes highlighted in red.
- POST /v1/image/classify ($0.002): Label an image with ResNet-50 (1,000 ImageNet classes): top-5 labels with confidence. Fast, cheap tagging for photos of animals, objects, food and scenes.
- POST /v1/image/fast ($0.004): Fast, cheap text-to-image with SDXL Lightning: a 1024x1024 image in about 4 seconds for $0.003. Width and height 256-1024, seed, negative prompt. Add store=true (+$0.001) for a share link.
- POST /v1/vision/ask ($0.004): Ask a question about an image (Moondream 3.1 vision model): read signs and screens, count things, describe a scene or check a photo. Without a question it writes a caption (short, normal or long).
- POST /v1/vision/locate ($0.004): Find things in an image by description (open-vocabulary detection): bounding boxes (mode=detect) or centre points (mode=point) for any phrase, e.g. 'the Submit button' or 'person in a red jacket', in 0-1 and pixel coordinates.
- POST /v1/translate/indic ($0.003): Translate English into 22 Indian languages with IndicTrans2 (AI4Bharat), which beats general translators on Indian languages: Hindi, Bengali, Tamil, Telugu, Marathi, Gujarati, Kannada, Malayalam, Punjabi, Urdu, Odia and more. Up to 50 texts per call.
- POST /v1/email/send ($0.01): Send one plain-text email to one recipient from agent@mail.agentrxi.com, with your display name and an optional reply-to. Every message carries a footer naming the AI sender with one-click unsubscribe. Anti-abuse: 20 emails per wallet per day (5 for new wallets), 2 per recipient per wallet, no phishing, credential requests, link shorteners or brand names; wallets that draw complaints are blocked.
- POST /v1/rooms ($0.005): Shared rooms where several agents (different wallets, different vendors) talk and coordinate: create a room ($0.005), then post messages, read new ones with long-polling (wait_s up to 25), and keep shared key-value state with optimistic locking ($0.002 per call). Kept 30 days after the last activity.
- POST /v1/queue ($0.002): Durable task queues for agents: push up to 100 items (with delay and priority), pop with a lease (visibility timeout) and long-polling, then ack or nack; peek and stats. Private to the wallet, or shared across wallets with a secret key. $0.002 per call, items kept 14 days.
- POST /v1/chat/completions ($0.0033): OpenAI-compatible chat completions on Meta Llama 3.1 8B, fast general chat. Set your OpenAI SDK base URL to https://agentrxi.com/v1 and pay per token with x402 instead of an API key: $0.135 per million input and $1.152 per million output tokens, minimum $0.002 a call, at most $0.0033. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (streaming supported), up to 2048 output tokens. Pass model to use any model listed at /v1/models (priced per that model).
- POST /v1/qwen/chat/completions ($0.0052): OpenAI-compatible chat completions on Alibaba Qwen3 30B mixture-of-experts, thinking model with tool calling, the cheapest chat here. Set your OpenAI SDK base URL to https://agentrxi.com/v1/qwen and pay per token with x402 instead of an API key: $0.153 per million input and $1.005 per million output tokens, minimum $0.002 a call, at most $0.0052. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (tool calling, reasoning, streaming supported), up to 4096 output tokens.
- POST /v1/gemma/chat/completions ($0.0058): OpenAI-compatible chat completions on Google Gemma 4 26B, reasoning and tool calling. Set your OpenAI SDK base URL to https://agentrxi.com/v1/gemma and pay per token with x402 instead of an API key: $0.3 per million input and $0.9 per million output tokens, minimum $0.002 a call, at most $0.0058. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (tool calling, reasoning, streaming supported), up to 4096 output tokens.
- POST /v1/glm/chat/completions ($0.0062): OpenAI-compatible chat completions on Zhipu GLM 4.7 Flash, reasoning and tool calling. Set your OpenAI SDK base URL to https://agentrxi.com/v1/glm and pay per token with x402 instead of an API key: $0.18 per million input and $1.2 per million output tokens, minimum $0.002 a call, at most $0.0062. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (tool calling, reasoning, streaming supported), up to 4096 output tokens.
- POST /v1/gpt-oss-20b/chat/completions ($0.0079): OpenAI-compatible chat completions on OpenAI gpt-oss-20b open-weight reasoning model with tool calling. Set your OpenAI SDK base URL to https://agentrxi.com/v1/gpt-oss-20b and pay per token with x402 instead of an API key: $0.6 per million input and $0.9 per million output tokens, minimum $0.002 a call, at most $0.0079. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (tool calling, reasoning, streaming supported), up to 4096 output tokens.
- POST /v1/mistral/chat/completions ($0.0104): OpenAI-compatible chat completions on Mistral Small 3.1 24B, tool calling and image input. Set your OpenAI SDK base URL to https://agentrxi.com/v1/mistral and pay per token with x402 instead of an API key: $1.053 per million input and $1.665 per million output tokens, minimum $0.002 a call, at most $0.0104. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (tool calling, image input, streaming supported), up to 2048 output tokens.
- POST /v1/llama4/chat/completions ($0.0125): OpenAI-compatible chat completions on Meta Llama 4 Scout, multimodal (image input) with tool calling. Set your OpenAI SDK base URL to https://agentrxi.com/v1/llama4 and pay per token with x402 instead of an API key: $0.81 per million input and $2.55 per million output tokens, minimum $0.002 a call, at most $0.0125. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (tool calling, image input, streaming supported), up to 2048 output tokens.
- POST /v1/gpt-oss/chat/completions ($0.0165): OpenAI-compatible chat completions on OpenAI gpt-oss-120b, the strongest open-weight OpenAI model, reasoning with tool calling. Set your OpenAI SDK base URL to https://agentrxi.com/v1/gpt-oss and pay per token with x402 instead of an API key: $1.05 per million input and $2.25 per million output tokens, minimum $0.002 a call, at most $0.0165. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (tool calling, reasoning, streaming supported), up to 4096 output tokens.
- POST /v1/coder/chat/completions ($0.0153): OpenAI-compatible chat completions on Qwen 2.5 Coder 32B for code generation, review and fixes. Set your OpenAI SDK base URL to https://agentrxi.com/v1/coder and pay per token with x402 instead of an API key: $1.98 per million input and $3 per million output tokens, minimum $0.002 a call, at most $0.0153. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (streaming supported), up to 2048 output tokens.
- POST /v1/nemotron/chat/completions ($0.0254): OpenAI-compatible chat completions on NVIDIA Nemotron 3 120B, agentic reasoning with tool calling. Set your OpenAI SDK base URL to https://agentrxi.com/v1/nemotron and pay per token with x402 instead of an API key: $1.5 per million input and $4.5 per million output tokens, minimum $0.002 a call, at most $0.0254. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (tool calling, reasoning, streaming supported), up to 4096 output tokens.
- POST /v1/large/chat/completions ($0.0199): OpenAI-compatible chat completions on Meta Llama 3.3 70B, strong general chat with tool calling. Set your OpenAI SDK base URL to https://agentrxi.com/v1/large and pay per token with x402 instead of an API key: $0.879 per million input and $6.759 per million output tokens, minimum $0.002 a call, at most $0.0199. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (tool calling, streaming supported), up to 2048 output tokens.
- POST /v1/deepseek-pro/chat/completions ($0.2158): OpenAI-compatible chat completions on DeepSeek V4 Pro, a top open frontier model with reasoning, tool calling and a 1M-token context. Set your OpenAI SDK base URL to https://agentrxi.com/v1/deepseek-pro and pay per token with x402 instead of an API key: $2.64 per million input and $7.92 per million output tokens, minimum $0.002 a call, at most $0.2158. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (tool calling, reasoning, streaming supported), up to 8192 output tokens.
- POST /v1/deepseek/chat/completions ($0.0720): OpenAI-compatible chat completions on DeepSeek V4 Flash, fast and inexpensive frontier model with tool calling and a 1M-token context. Set your OpenAI SDK base URL to https://agentrxi.com/v1/deepseek and pay per token with x402 instead of an API key: $0.88 per million input and $2.64 per million output tokens, minimum $0.002 a call, at most $0.0720. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (tool calling, reasoning, streaming supported), up to 8192 output tokens.
- POST /v1/kimi/chat/completions ($0.1742): OpenAI-compatible chat completions on Moonshot Kimi K2.6, an agentic model built for long tool-calling workflows (262K context). Set your OpenAI SDK base URL to https://agentrxi.com/v1/kimi and pay per token with x402 instead of an API key: $1.9 per million input and $8 per million output tokens, minimum $0.002 a call, at most $0.1742. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (tool calling, reasoning, streaming supported), up to 8192 output tokens.
- POST /v1/kimi-code/chat/completions ($0.1742): OpenAI-compatible chat completions on Moonshot Kimi K2.7 Code, a coding and software-agent model with tool calling (262K context). Set your OpenAI SDK base URL to https://agentrxi.com/v1/kimi-code and pay per token with x402 instead of an API key: $1.9 per million input and $8 per million output tokens, minimum $0.002 a call, at most $0.1742. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (tool calling, reasoning, streaming supported), up to 8192 output tokens.
- POST /v1/glm5/chat/completions ($0.2322): OpenAI-compatible chat completions on Zhipu GLM-5.3, frontier reasoning with tool calling and a 1M-token context. Set your OpenAI SDK base URL to https://agentrxi.com/v1/glm5 and pay per token with x402 instead of an API key: $2.8 per million input and $8.8 per million output tokens, minimum $0.002 a call, at most $0.2322. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (tool calling, reasoning, streaming supported), up to 8192 output tokens.
- POST /v1/glm5-flash/chat/completions ($0.0381): OpenAI-compatible chat completions on Zhipu GLM-5.3 Flash, inexpensive reasoning with tool calling and a 1M-token context. Set your OpenAI SDK base URL to https://agentrxi.com/v1/glm5-flash and pay per token with x402 instead of an API key: $0.45 per million input and $1.5 per million output tokens, minimum $0.002 a call, at most $0.0381. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (tool calling, reasoning, streaming supported), up to 8192 output tokens.
- POST /v1/qwen3.8/chat/completions ($0.1039): OpenAI-compatible chat completions on Alibaba Qwen 3.8 27B, the newest Qwen with reasoning, tool calling and a 262K context. Set your OpenAI SDK base URL to https://agentrxi.com/v1/qwen3.8 and pay per token with x402 instead of an API key: $0.9 per million input and $6.4 per million output tokens, minimum $0.002 a call, at most $0.1039. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (tool calling, reasoning, streaming supported), up to 8192 output tokens.
- POST /v1/qwq/chat/completions ($0.0315): OpenAI-compatible chat completions on Alibaba QwQ 32B, step-by-step reasoning for math and logic. Set your OpenAI SDK base URL to https://agentrxi.com/v1/qwq and pay per token with x402 instead of an API key: $1.32 per million input and $2 per million output tokens, minimum $0.002 a call, at most $0.0315. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (reasoning, streaming supported), up to 8192 output tokens.
- POST /v1/r1/chat/completions ($0.1084): OpenAI-compatible chat completions on DeepSeek R1 Distill (Qwen 32B), chain-of-thought reasoning model. Set your OpenAI SDK base URL to https://agentrxi.com/v1/r1 and pay per token with x402 instead of an API key: $0.994 per million input and $9.762 per million output tokens, minimum $0.002 a call, at most $0.1084. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (reasoning, streaming supported), up to 8192 output tokens.
- POST /v1/granite/chat/completions ($0.0029): OpenAI-compatible chat completions on IBM Granite 4.0 Micro, the lowest-cost chat here, with tool calling (131K context). Set your OpenAI SDK base URL to https://agentrxi.com/v1/granite and pay per token with x402 instead of an API key: $0.051 per million input and $0.336 per million output tokens, minimum $0.002 a call, at most $0.0029. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (tool calling, streaming supported), up to 4096 output tokens.
- POST /v1/sea-lion/chat/completions ($0.0370): OpenAI-compatible chat completions on AI Singapore SEA-LION v4 27B, tuned for Southeast Asian languages (Indonesian, Thai, Vietnamese, Filipino, Malay and more). Set your OpenAI SDK base URL to https://agentrxi.com/v1/sea-lion and pay per token with x402 instead of an API key: $1.053 per million input and $1.665 per million output tokens, minimum $0.002 a call, at most $0.0370. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (streaming supported), up to 4096 output tokens.

## How to pay
Any x402 client works: @x402/fetch, Coinbase AgentKit, Cloudflare Agents SDK withX402Client, x402-wallet CLI. Fixed price per request; the exact amount is in the 402 response. Over MCP, use an x402-capable MCP client (@x402/mcp).