Data x402 offerings

Extract tabular data from messy text or HTML using Claude Haiku — detects columns and rows in unstructured content and returns clean structured JSON (columns + rows) so agents can turn pasted tables,…

Extract structured data from invoice or receipt text — or directly from an invoice URL (PDF, HTML, or plain text, fetched and parsed server-side) — using Claude Haiku: returns vendor, invoice number,…

Split text into overlapping chunks for RAG ingestion — by characters or words, with configurable chunk size and overlap. Deterministic (same input → same chunks), returns each chunk with its index an…

Normalize any messy money string into a typed decimal amount plus ISO 4217 currency — handles symbols, locale separators ($1,234.56 vs €1.234,56), magnitude suffixes (1.2M), accounting notation, and …

Extract named entities from text using Claude Haiku — people, organizations, locations, dates, emails, URLs, money amounts, and products — returned as structured typed arrays so agents can pull struc…

Turn unstructured text into structured JSON matching a caller-supplied schema using Claude Haiku — the agent declares the fields and types it wants, and gets back populated JSON with values pulled fr…

Parse a PDF to text and Markdown: send a PDF url or base64 file, get clean Markdown with paragraphs rebuilt from the text layer, per-page character offsets for citing pages, metadata (title, author, …

Parse and normalize a freeform address string using Claude Haiku — splits it into street, city, state/region, postal code, and country, plus a normalized single-line form, so agents can clean and sta…

Extract structured data from any unstructured text into your own JSON Schema — structured-data / information extraction, text-to-JSON, LLM data enrichment. You supply the schema; the LLM returns a ma…

Extract structured contact details from text, an email signature, or webpage text using Claude Haiku — returns name, title, company, email, phone, and address as clean JSON so agents can turn unstruc…

Validate data against a supplied schema — checks required fields, nested objects, arrays, enums, string formats, numeric ranges, lengths, and additional-property rules deterministically, with optiona…

Conform messy or inconsistent JSON to a target schema using Claude Haiku — renames keys, coerces types (string→number, "true"→boolean, etc.), and fills missing fields with null, returning JSON that m…

Remove duplicate rows by exact key, keeping the first or last, and report conflicting columns per group.

Use when an agent needs keyword extract. Returns Ranked keyword and named-entity extraction from text, returned as clean JSON arrays — parse-validated with one automatic retry. $0.004.

Use when an agent needs extract json. Returns Extract structured JSON from unstructured text against a caller-supplied JSON Schema — parse-validated with one automatic retry, 502 on failure instead of garbage. $0.01.

Clean and normalize whitespace in text for downstream agent processing

Any Eurostat dataset (thousands: unemployment, GDP, population, house prices, energy, trade, tourism, transport...) by dataset code, with optional dimension filters as query parameters (e.g. geo=NL, unit=PC_ACT) and lastTimePeriod. Returns labelled observations (max 500). Use it for official European statistics. Eurostat data, CC BY 4.0; values unchanged.

Any OECD dataset via the OECD SDMX API: give the dataflow (e.g. OECD.SDD.STES,DSD_STES@DF_CLI for leading indicators) and a series key with country codes (e.g. NLD........), and get the latest observations with dimension labels (max 500). Use it for international macro and social indicators across OECD countries. OECD data, CC BY 4.0 (third-party data excluded).

Any Statistics Netherlands (CBS StatLine) table by table id, e.g. 83625NED (house prices), 85773NED (population), 70072NED (regional key figures): one row per value with its dimensions, measure code, measure title and unit, optional OData $filter and $select, up to 500 rows, plus the table title and last update. Use it for official Dutch statistics. CBS open data, CC BY 4.0.

Flag outliers in a numeric series using either the IQR rule (Tukey fences at 1.5·IQR - robust, default) or z-score (|z| > threshold - assumes normality). Returns the outlier values + their indices + the thresholds used so you can decide whether to trust them.

Usage info for the html-clean tool: pay this GET once to receive machine-readable instructions, then call POST /html-clean to turn raw HTML into clean structured content (title, meta, LLM-ready text, headings, links, images).

Coinbase's tokenized U.S. stocks on Base (B20): each token's contract, underlying ticker, live Chainlink 24/5 price (USD) with updatedAt, and minted supply (0 = no secondary liquidity yet; the quote decides). GET /v1/stocks. Secondary trading is permissionless on-chain; Regulation S, not for U.S. persons or other restricted jurisdictions.

Split a web page's readable text into ~512-token chunks with 0-token overlap, breaking on sentence boundaries, for embeddings and RAG. Returns the chunks in order with their approximate token counts, the page title and total chunk count. One preset, no parameters to get wrong. $0.01 per page.

Sentence statistics of a page for Arabic text: sentence count, average and longest sentence length, share of questions and exclamations, the detected language, and the five longest sentences (readability red flags). Arabic-aware splitting for CJK/Thai scripts where sentence marks differ. $0.01 per page.