What Agents Buy.

I paid 10 brand-new x402 sellers and checked every answer. All 10 were right.

Most new sellers never get a single customer, so I became one. I picked 12 that showed up since Sept 4, each a cent or two, and paid each once. Ten sold to me, for 5.1 cents total.

92% of wallets paying for x402 APIs only pay one seller

I started tracking who pays, not just who gets paid. From Sept 11 to 17, 5,445 wallets paid an x402 seller on Base. 5,012 of them (92%) paid just one.

AnswerPool serves Apple's 2018 revenue as its latest

Agents are starting to pull company fundamentals over x402 instead of buying a data terminal, and AnswerPool sells exactly that: SEC numbers by the call, a few cents each, no signup. Most of it is genuinely good. But I paid it to compare the latest revenue of Apple, Nvidia, and Microsoft, and it reported Apple at 62.9 billion dollars dated September 2018 and Microsoft at 20 billion dated December 2010, both labeled latest reported. One retired XBRL tag explains all of it, and it quietly poisons the single number people ask a fundamentals API for most.

My own grader flagged 20 sellers for overcharging. The chain cleared 16 of them outright; the other four never had a settled payment to check. Zero overcharges confirmed. The liar was my payment client, not the sellers.

Grading 750 new sellers, my harness flagged 20 as charging more than they advertised, most often listed at $0.015 with my client reporting $0.020. Twenty overcharges is a story. It is also an accusation against 20 named businesses, so before it went anywhere I did the thing this site is built on: I checked the chain.

I ran our own report card. For seven days I lined up every verdict we give agents against the money that actually moved on chain. Sellers we cleared took 99.8% of every dollar. The 51 we told agents to abort on took nothing.

We give every x402 seller a pre-payment verdict: CLEAR, HOLD, or ABORT. The obvious question is whether that verdict is any good. So I joined it against the settlement tape, the real USDC agents paid each seller over the last seven days, and looked at where the money actually went.

New sellers show up on x402 every day, and almost nobody has ever paid them. This week they ranged from nautical charts to quantum circuits. I bought the genuinely new ones and checked what came back: four delivered exactly what they promised, and a depeg monitor that advertises two cents quoted five.

The market lists new sellers constantly, and most of them nobody has ever paid, which is the gap this site exists to fill. So I pulled everything that appeared in the last week, set the factory-spam aside (one host alone sprayed 335 endpoints), and bought the ones that looked genuinely new: a nautical chart oracle, a grant database, a UK company registry, a Hyperliquid whale tracker. One call each, every response archived, judged against the seller's own declared output.

I had been grading the corner of x402 with a right answer, the crypto and stock and gas prices. That is about a seventh of the market. I pointed the wallet at the whole thing for sixty cents, and the first endpoint my agent paid looked it in the eye and said NGMI.

For weeks I had been measuring the objective slice of x402, the feeds you can check against a primary source. It is the easy part, and it is a fraction of what is out there. So I stopped narrowing, pointed the wallet at the entire market, and bought whatever looked interesting, one call each. Sixty cents later, here is what an AI agent can actually purchase today, every line with a transaction hash behind it.

Across 17 days and 6.4 million agent payments, 96% came from sellers whose volume is a single dominant wallet. Those sellers moved 28% of the dollars. The payment count this market gets quoted by is mostly one relationship repeating itself.

x402 is usually sized by transaction count, because the counts are enormous and the dollars are not. On the repaired tape, 6,386,618 payments settled between 2026-08-04 and 2026-08-20. Only 229,144 of them, 3.6%, went to sellers whose money came from a spread of independent buyers. The other 96.4% went to sellers where one wallet supplied 90% or more of that day's dollars. By dollars the picture inverts: 72% of the money went to the broadly held sellers. Both numbers are on the live dashboard.

I audited my own settlement tape against the chain and found it undercounting agent payments by 4.2x. Three days did not exist at all and two more were recorded as real zeros. The run that lost the most data looked the healthiest of them all, failing under 2% of its queries.

Every settlement figure on this site comes from sweeping USDC Transfer logs on Base. On 2026-08-21 I found the sweep had been holding a single RPC endpoint for an entire run and writing off any block range that endpoint refused to serve. I re-swept every day from 2026-08-04 to 2026-08-20 with failover across providers and recursive splitting of oversized ranges, and recorded a day only when zero ranges were left unserved. The repaired tape holds 6,386,618 payments where the old one held 1,508,017. Every number this site published from that tape was low, and the leaderboard has been corrected in place.

I paid 8 x402 APIs for Apple's live stock price and graded each against a professional feed. Seven matched to the penny at $305.93. The only one that drifted, by 30 cents, was also the most expensive, at ten times the price of the accurate ones.

Financial Modeling Prep sells a professional real-time stock feed. I wanted to know whether the cheap x402 APIs reselling stock quotes actually match it, so I paid eight of them for Apple's live price at the same moment and graded each against FMP's number, $305.93. Seven came back at $305.92 or $305.93, matching to the cent. It is the same result as every other objective-truth category on this site: when the answer is a fact, nobody gets it wrong.

Preflight is live: before your agent pays any x402 API, it gets one verdict, CLEAR, HOLD, or ABORT. As it stands today, 20 of 1,081 sellers are payment traps and 80 resell data you can get for free.

An AI agent can hold a wallet and spend it on its own, but until now it had no way to ask one simple question before the money left: is this seller safe to pay, and will it actually deliver? Preflight answers that in a single call. Point it at any x402 endpoint and it returns one verdict the agent can gate on, CLEAR, HOLD, or ABORT, built from everything this site has measured by paying the market with a real wallet.

Most of what agents pay for is free. I bought a web search for a tenth of a cent, then ran the same search myself for nothing and got more. Here is the slice that is actually worth paying for.

An AI agent can search the web, read a blockchain, and hit a free weather endpoint on its own. So why is so much of the x402 economy selling it exactly those things? I paid two web-search APIs a tenth of a cent each to look up "x402 payment protocol." Then I ran the identical search with my own free tool and got ten results and a written summary instead of five links, at no cost. That is not a gotcha, it is the shape of an entire category, and the week's measurements say so.

I asked 12 APIs for one wallet's USDC balance on Base. The 7 that answered were exact to the cent. The other 5 gave me ETH, a whole portfolio, or an error, because "balance" means five different things.

Wallet balance lookups are the most-paid category in the whole x402 market, 217 buyers and about $69,000 a day. So I read one address's USDC balance straight off Base, $30.464119 held by vitalik.eth, and paid twelve balance APIs to tell me the same number. Seven returned a USDC figure and every one was exact to the cent. That is the whole point, and the reason is worth sitting with.

I let my agent's wallet loose in the x402 economy with a dollar. For four cents it bought a roast, a blessing, a chess puzzle, and, when it asked for the price of gas, actual natural gas.

Underneath the price feeds and the sanctions screens, the x402 economy has a soul, and it is a very strange one. So I gave my agent's wallet a budget and bought the twelve oddest things I could find, one call each. It cost four cents, eleven of the twelve delivered, and what came back is the best argument I have that this market is real: nobody builds a signed-absolution endpoint for a demo.

I fed three OFAC-sanctioned wallets to three sanctions-screening APIs. One flagged all three, one would block them but mislabels the match, and one only reads the wrong chain.

Sanctions screening is the one category with a clean, public answer key: the OFAC SDN list. So I took three addresses that are currently on it and two clean controls (one of them my own wallet) and paid three services that sell wallet screening to check each one. Nobody let a sanctioned wallet through, which is the good news. The interesting part is how differently the three behave once you actually pay and look, and none of that is visible from a free check.

I bought the temperature in New York from 12 weather APIs. Four returned the exact same bytes. Only one used the official US source, and it said so.

There is no single true temperature either, so I did not grade these against another weather API. I read the official observation from the National Weather Service station in New York, 84 degrees at KNYC, and then paid 12 sellers a tenth of a cent each, overriding every one of their location inputs to the same city. Seven returned a temperature and all were within about two degrees of the station. The accuracy is not the story. The story is that most of these are not really different services.

I asked 10 APIs for the gas price. The blockchain ones agreed to the same fraction of a gwei. One gave me the price of natural gas.

Gas is the cleanest thing to check on this whole site, because the answer is not a vendor's opinion, it is a number the chain publishes in every block. So I read the base fee straight from Base's latest block, 0.005 gwei, and then paid 10 sellers a tenth of a cent each for the current gas price. Six returned a real blockchain gas price and all six sat right on the chain's base fee. The other four are the story, and one of them sells the price of natural gas.

I paid 15 APIs for the price of Bitcoin. The 8 that answered were all within 0.1% of the exchange. The other 7 were selling prediction markets, candles, or a CoinGecko passthrough that had already broken.

There is no single true price for Bitcoin, so I did not grade these against another price API, which would just measure which vendors agree. I graded them against a primary reference: the median of Coinbase and Kraken spot at the same second, which happened to agree to three thousandths of a percent. Then I paid 15 sellers a fraction of a cent each for the current BTC/USD price. Eight returned a real spot price and every one landed within 0.12% of the exchange, most within 0.02%. The interesting part is the other seven, and what the word price turns out to mean.

I scanned every payment into the top 60 services for a week. 2,864 wallets sent 1.09 million payments, and a single wallet sent 90% of them.

The market brags about payment volume. So I read it directly: every USDC payment into the payTo wallets of the 60 highest-revenue services on Base, for a week, grouped by who sent it. 2,864 wallets sent 1,088,819 payments worth $202,065. That looks like a broad, busy market. It is not. 975,292 of those payments, 89.6% of the whole count, came from one wallet paying one service, roughly 1.6 payments every second for seven days. Take that single wallet out and the payment count drops nine-fold.

I paid 345 agent APIs to see if they return the fields they advertise. 306 did. 39 took the payment and returned a response missing fields they promised, and only paying reveals which 39.

Every x402 seller ships a schema: send this input, get these fields back. That is a promise, and almost nobody checks whether it holds, because checking means paying. So I paid. I sent each endpoint the exact input its own listing advertises, then compared what came back, field by field, against the output the same listing promises. I ran 549 endpoints through it. 345 returned a clean enough response to judge; of those, 306 delivered everything they promised, 89 percent, and 39 fell short. The other 204 could not be judged at all, and that gap is a finding in itself. Before recording a single shortfall I called that endpoint a second time, so nothing here rests on one bad response.

We measured this market on Base for a week. Then we swept Solana and found 53% of the money was settling there, on a chain we were not reading.

Every settlement number this site has published was swept from Base, because Base is where most x402 tooling points and it is the easy chain to read. We flagged the gap in writing and even proved it by making a payment of our own that our tape never saw. This week we finally swept Solana too. It carried $75,952 in a single day against Base's $66,440, so the chain we were not looking at held 53% of the market. The leaderboard was not slightly off. It was showing a minority of the money.

I bought 200 dice rolls and tested whether they were actually random. They were.

Agents use randomness for real decisions: sampling, tie-breaking, retry jitter, loot drops. api.anchor-x402.com sells it for a tenth of a cent a call and calls it a drop-in VRF for game studios. Nobody appears to have checked whether a paid randomness endpoint is random, so I bought two hundred rolls of a twenty-sided die and ran the tests. It passes. The part it does not pass is the word verifiable.

I paid an API to audit my own spending, then checked its arithmetic against the chain. It was exact.

This site keeps its own record of every payment it has ever made, and sweeps Base itself, which makes it about the only buyer able to mark an accounting API's homework. So I paid api.anchor-x402.com a cent to audit my own wallet and then checked every number against my own sweep of the chain. It agreed on all of them.

It resells Exa for two tenths of a cent and shows you its own cost in the receipt

Exa is a web search and page-reading API that normally wants an account, an API key and a card on file. enrichx402.com is a reseller: it holds the Exa account, takes your request, calls Exa with its own key and hands the answer back, charging you per call in USDC with no signup at all. That is the whole point of this category, and it means two resellers of the same upstream can be compared on identical goods, because blockrun.ai sells the same Exa call. I pointed it at a page on this site, so I knew exactly what a correct answer looked like. It quoted two tenths of a cent, charged two tenths of a cent, returned the right text, and then did something no other seller here has done: it told me what the call had cost it.

One seller publishes its own fee split, and the payment rail costs ten times the thing being sold

Almost every x402 challenge quotes a single number. api.surplusintelligence.ai, which sells OpenAI-compatible inference and has taken $19,013 in seven days, itemises it instead. Its challenge reports an estimated cost of $0.003302 for a small gpt-4o-mini call, of which $0.003000 is a flat x402 facilitation fee. The inference is about three hundredths of a cent. The rail costs ten times the goods, and the seller says so in the response.

For $190 a year, a company will pay your own API twice a month so the directory thinks you have customers.

Coinbase's Bazaar shows how many calls and how many distinct wallets each listed API got in the last 30 days. That number is how anyone tells a live service from a dead one, which makes it the thing a new seller most wants and least has. Somebody noticed the number is a payment, and a payment is a thing you can buy. mudko.com sells exactly that, openly, as a listing inside the directory it is gaming.

Someone is faking blockrun.ai's payment address. Its biggest customer has paid 732,761 times since and never missed.

blockrun.ai sells stock quotes and web search by the call. It takes more individual payments than any other service on the tape and almost all of them come from a single wallet. Starting 2026-08-09 someone began generating addresses that begin and end with the same characters as blockrun.ai's real payment address, then sending a speck of USDC from each one so it would land in that customer's transaction history. Truncated, all 89 counterfeits read 0xe9030…1abf. So does the real address. blockrun.ai did nothing wrong here; the attack is aimed at the wallet paying it.

I asked six trust services about a counterparty I can prove takes money and delivers nothing. One caught it.

Two hundred services in the registry now sell trust: reliability pre-flights, reputation scores, merchant screening, attested delivery. I have one counterparty I can prove charged twice and returned nothing, with the transactions on chain. So I paid six of them to look at it.

The only service that noticed I had been robbed, and it did not charge me

Six services were asked about a counterparty that charged me twice and delivered nothing. Five scored its reputation and found nothing wrong. groundcheck.seiche.info asked a different question, got the right answer, signed it, and did not bill me.

A trust index charged a cent to tell me a service was fine, using data five weeks old

Part of the trust-layer test. aeml-x402.zeabur.app scored a counterparty I can prove is broken as live and operating, which would be a serious miss except that it tells you, at some length, that its data is 35 days old and most of its fields no longer exist.

Three sellers, one gas price, a tenfold spread. The middle one is the worst deal.

Base gas price is a single number anyone can read for free, and three sellers charge between a tenth of a cent and a cent to hand it to you. I bought all three inside thirty seconds and checked them against the chain. Every one was right, and the cheapest gave the most.

Five email checkers, one address that cannot receive mail. All five caught it.

Eleven sellers in the registry validate email addresses, priced from a tenth of a cent to two and a half cents. I sent five of them, 2s.io among them, the same address: correct syntax, a real domain that resolves, and no mail server at all. It is the test that separates a regex from a lookup.

It charged me three tenths of a cent and returned its own homepage

keyronne.com is my mistake and their defect at the same time, which makes it the most useful entry of the session. I called it the wrong way. It took the money anyway and sent me a web page. Then I called it correctly and it behaved better than almost anything else I have paid.

A second settlement verifier confirms the payment its seller said had failed

quartermaster.surewhynot.app is the second independent check on the transaction an endpoint told me twice had failed to settle. Three tenths of a cent, and it agrees with the chain and with the other verifier I paid an hour earlier.

The directory of the agent economy grew 1% last week. A fifth of it was replaced.

The registry looks stable. It held 14,668 resources on 4 August and 14,828 on 10 August, a gain of about one percent. Underneath that, 2,803 endpoints appeared and 2,643 disappeared. Almost none of it was the market growing, and most of it was a handful of people.

The endpoint that would have caught what jarvisclaw denied, for a fifth of a cent

Two days ago an endpoint charged me twice while telling me settlement had failed, and I believed it. x402.halowerk.com costs two tenths of a cent and answers exactly that question. I fed it the transaction the other seller said did not exist.

Two services, the same wallet, fourteen seconds apart. Both right, one shows its work

The first head to head on this site. I asked anywaypossible.com and signals.edge.report the same question about the same wallet within fourteen seconds and checked both against the chain. They gave different numbers. Both were correct, and the reason why is the whole point.

Correct to the last decimal, but it will not say when it looked

The other half of the head to head. signals.edge.report answered correctly, cheaply and instantly, and the only thing keeping it from an A is that it will not tell you which block it read.

I paid Nansen two cents to check my own wallet and it found money I did not know had gone

The first name most people would recognise to show up on the settlement board. I pointed it at the one wallet whose entire history I control, expecting to check its arithmetic. It was exact to the microdollar on every day, and one of those days did not match my own records.

Most wallets paying for things on Base have never sent a transaction

Nansen returned nothing when I asked who first funded my agent wallet. That answer is correct, and it points at something structural: an agent wallet can move real money for a week without ever touching the chain as a sender. I checked whether that is normal. It is.

Two thirds of x402 sellers put the price somewhere a body parser will never look

Yesterday a rival grader failed BlockRun because it only read the response body. I wanted to know how big that mistake is, so I probed 220 origins and looked in all three places the spec allows. It is not an edge case. It is most of the market.

A census API that is accurate in cities and silently wrong in small towns

x402datasource.com charges a cent per lookup for population and income around an address. It billed exactly what it quoted three times out of three and geocoded every address correctly. Then I asked it about a town of fifteen hundred people and it told me twenty-six people live there.

It said the payment failed. It took the money twice.

I graded api.jarvisclaw.ai a D two days ago and wrote that nothing had been charged, because my client reported the payment as null and the endpoint returned a settlement error. Both were wrong. The chain shows two payments left my wallet, one for each attempt, and no data ever came back.

A trust-score API charged me for a lookup that missed, on the address in its own listing

api.thetrustlayer.xyz is the third grader to appear in this market in a week, and the first that scores agents rather than endpoints. I paid a tenth of a cent to look up the one agent address it advertises in the public registry. It has 393,945 agents indexed. That one is not among them, and I was charged anyway.

A rival grader failed the busiest service in the market because it never read the header

x402lint appeared in the registry today grading the same sellers I do, from the outside, without ever paying. Its reports are free to read, so I read the two it holds for services I have bought from. Both are graded F with a score of zero, and both zeros trace back to it not reading what the seller published.

FortClaw quotes honestly and then tells you nothing when you get it wrong

Tenth on the revenue board. Its prices are honest, which is more than the biggest earner manages. But I could not buy anything from it for three cents, and it would not tell me why.

BlockRun charges the same fifth of a cent for a $0.03 model and a $5 model

BlockRun takes more payments than the rest of the agent economy combined, 136,284 in a day at an average of five cents. I paid it two tenths of one cent for a flagship model and got exactly what I paid for.

BlockRun's free tier is real but not currently callable. The two-models-one-name finding from August 7 no longer has a subject, and as of August 28 the free pool is exhausted on all five models, so there is nothing left to grade.

On 2026-08-07 BlockRun advertised six free chat models needing no wallet, and I asked all six the same thirty-six questions. Two turned out to be the same model wearing different names. Re-tested on 2026-08-28, that catalog no longer exists and the free pool will not answer at all, so this is published as an observation rather than a grade.

Bitrefill sells 594 real gift cards to agents and charges a fifth of a cent to browse

Bitrefill is the second largest earner in the agent economy and the only one near the top selling something a human can actually use. I spent three tenths of a cent browsing its catalogue and it charged exactly what it said it would, twice.

The biggest earner in the agent economy publishes one price and quotes another

x402.Boats takes more money than anything else agents pay for. I could not complete a purchase from it, and the thing that stopped me was not the payment. It was that nothing it says lines up, and nothing it returns tells you what went wrong.

CoinMarketCap returns up to 32 assets for one ticker symbol

If your agent looks up a coin by ticker, it is not asking a precise question. I paid a cent a time to count how many separate assets claim the same symbol.

CoinMarketCap charges $0.01 per call and quotes it on seven chains

I found what looked like the most expensive thing in the agent economy: a CoinMarketCap price quote listed at ten billion dollars. I was about to grade it F. Then I paid it, and it charged one cent.

StableMemes delivers a captioned meme for $0.01, charged as quoted

I gave an agent a wallet and told it to buy something. It found a meme API, read the price off the paywall, signed a payment, and got back a JPEG. No account, no API key, no card.

Cloudflare launches stablecoin wallets for AI agents