Market data your AI agent can buy on its own.

Twenty-three years of minute-by-minute prices for every US stock. Your agent asks a question, pays a fraction of a cent, and has its answer in milliseconds. No API keys. No subscriptions. No one filling out a signup form.

23 yrs
of history, 2003 to today
16,000+
tickers on active days
1 min
bar granularity, full OHLCV
$0.005
queries start here
How it works

One request. One payment. Done.

Traditional data vendors were built for humans — contracts, sales calls, monthly minimums. Cabrini is built for software that buys what it needs, when it needs it, using the x402 payment standard.

1

Ask for data

Your agent requests any ticker and date — Apple on the day the iPhone launched, or every symbol that traded last Tuesday.

2

Pay in passing

The response quotes an exact price. The agent signs a USDC micropayment on Base and retries — no account, no invoice, no human.

3

Get the full day

Around 390 one-minute bars come back — open, high, low, close, volume, and trade count for every minute of the session.

# Ask POST /v1/query {"ticker": "AAPL", "date": "2024-01-02"} # Server quotes the price 402 Payment Required · $0.025 USDC on Base # Agent signs, retries with proof POST /v1/query + PAYMENT-SIGNATURE # Data arrives 200 OK · 390 minute bars for AAPL
Pricing

Pay for the question, not the platform.

Every price is quoted up front in the response itself. No tiers, no seats, no minimum spend — a research run that costs a dollar today costs nothing tomorrow if you don't run it.

POST /v1/query
$0.025
One ticker, one full trading day — about 390 minute bars.
GET /v1/tickers
$0.005
Every symbol that traded on a given date — 7,000 to 16,000+.
POST /v1/range
$0.01 / day
One ticker across multiple days, up to 20 at a time.
POST /v1/batch
$0.02 / ticker
Up to 25 tickers for a single date in one request.
The data

Deep enough for real research.

This isn't a sample set. It's the full US equity market at one-minute resolution, from September 2003 through the present, cleaned and refreshed on an ongoing basis.

Every US equity

Large caps, small caps, ETFs, and the long tail — everything that printed a trade, including symbols that have since delisted.

Minute-level OHLCV

Open, high, low, close, volume, and transaction count for each minute, with nanosecond-epoch timestamps.

Two decades of context

The 2008 crisis, the flash crash, the meme-stock era — 23 years of market behavior to train on and test against.

Clean and consistent

Gap-checked and normalized to one schema across the entire archive, so 2003 parses exactly like 2026.

Wiring up an agent?

Cabrini speaks the protocols agents already understand — connect over MCP, discover via A2A or llms.txt, pay with x402. Everything technical lives in one place.

MCPA2Ax402OpenAPIllms.txt
Agent integration guide