What Agents Buy.

Independent reviews of the x402 APIs behind agentic commerce. I give an AI agent a real wallet, buy things with it, and publish every receipt.

Written by Neil·nothing here is sponsored·new? start here

25bought and graded
81agent calls this week

I pay for these APIs with my own wallet and publish what happened. The volume this market gets quoted by is mostly wallets paying themselves, so I read the payments off the chain myself. I check whether the answer that comes back is actually right, against a source that cannot be the seller. And the verdict an agent gates on is backed by money that moved. The sweep covers every USDC payment agents make on Base and Solana, every day. Free MCP server for your agent →

Why this differs from the x402 dashboard total

This headline counts USDC received at the seller wallets we track, on Base and Solana, over the last complete UTC day. Of it, $32,513 settled on Base and $77,587 on Solana (Solana is mostly Bitrefill and Laso). The /x402 dashboard sweeps Base only, so it shows roughly the Base portion; a rolling-24h window there also differs from a calendar day by a few percent. Every figure on this site carries its scope for exactly this reason.

How we grade

Every seller gets graded on four questions. Two are checked for free on every seller, every day. The other two only get graded after I have paid.

QuestionCostWho gets checkedWhere to see it
1. Does the paywall work?FreeEvery listed seller, daily (4,018)Preflight
2. Did it deliver?PaidSellers I have bought fromDelivery checks
3. Was the answer right?PaidCategories with one right answerAccuracy
4. Is the demand real?FreeEvery seller that got paidReal demand

1. Does the paywall work?

Before paying anything, I ask each seller for its price and check what comes back. That gives a score out of 100.

What is checkedPoints
The listed pages respond at all15
They answer with a proper payment request (HTTP 402)15
That request has everything an agent needs to pay25
The live price matches the listed price, within 2%15
It pays to the address on file, or rotates addresses by design10
It publishes discovery docs (6) and an input schema (4)10
Median response under 0.4s gets 10, under 1s 7, under 2.5s 4, else 110
Penalty: it charges for pages that do not exist−30
Bonus: it has free pages to try first+3

A is 85+, B is 70+, C is 55+, D is 40+, anything lower is F. Right now: 1,908 A, 586 B, 19 C, 63 D, 88 F, plus 1,354 with nothing I could test.

2. Did it deliver?

I pay once, using the example input from the seller's own listing, and check the response against the fields the seller promised.

So far: 831 delivered and 95 short. Every charge is matched to the payment on chain, and every raw response is saved before it is graded.

3. Was the answer right?

Where a question has one right answer, I compare what the seller returned with a primary source, never another reseller.

What I askChecked againstRight if within
BTC/USD spot priceCoinbase/Kraken median1%
AAPL real-time priceFMP real-time quote1%
EUR/USD rateECB reference rate0.5%
Base gas base fee (gwei)Base chain latest block0.01 gwei
USDC balance of vitalik.eth on BaseBase chain balanceOf0.01 USDC
New York temperatureOpen-Meteo (New York)5 °F

A seller can return every promised field and still get the number wrong, which is why this is its own grade.

4. Is the demand real?

From the blockchain, I look at who actually pays each seller and score the shape of that demand out of 100.

PartPoints
How many different wallets paid (full marks at 100)40
How evenly the dollars are spread across those wallets40
How many buyers came back (full marks at 30%)20

Revenue is left out on purpose. A big number does not prove anyone wanted the product. A score under 40 is flagged, and so is any seller where one wallet supplies 90% or more of the money. That describes the shape of the demand, not wrongdoing: one big real customer looks the same on chain as a seller paying itself.

How it adds up: one verdict before you pay

Agents get a single verdict per seller from Preflight.

VerdictWhenRight now
CLEARPositive evidence and nothing wrong: the price and payment address match, and any paid calls delivered.1,803
HOLDSomething to check first: the live price does not match the listing, a short delivery was confirmed twice, or an answer was wrong.130
ABORTHard evidence only: it pays to a different address than it lists, charges for pages that do not exist, or took full payment and returned nothing, twice.55
UNRATEDNo data yet.751

Each verdict also says how much it rests on. Verified means a payment to that seller settled and gave me a result I could grade (653). Probe only means the free check (1,335). Unproven means listed, with nothing measured yet (751).

The letter grades on reviews

When I write up a purchase, the grade (A+ to F) is for one named behavior, like price honesty or revenue accuracy, not the whole company. The verdict is one of Honest, Overcharged, Partial or No goods. So one seller can hold an A for price honesty and a D for accuracy. AnswerPool is the example: most of its SEC data was fine, but it served Apple's 2018 revenue as current, so it got a D on revenue accuracy.

Rules I hold myself to

Every term is defined in the glossary. The grading code is public at github.com/neilkpatel/whatagentsbuy.

Counts as of 2026-09-17 · free probe of 4,018 sellers, paid receipts, Base chain.