Browse indexable data x402 offerings, including provider, method, and service details.
989 indexable offerings in this category.
Reconcile up to 80 committee-aggregate or non-personal organizational public/synthetic campaign ledger entries against declared opening and closing balances. Flags duplicate IDs and missing document references. Individual-contributor records are prohibited, including hashed or redacted records. Caller must attest authorized commercial use. No contribution intake, payment execution, filing or legal compliance verdict.
Reconcile up to 80 committee-aggregate or non-personal organizational public/synthetic campaign ledger entries against declared opening and closing Supplied-record analysis, not independent certification. Full contract at the free describe URL.
Compare two structured celestial result declarations using versioned rules. Reports mismatched conventions and missing prerequisites. No inferred settings, time/frame conversion, calculation verification or predictive validation. New modular adapter: retained result recovery for 24 hours, minimal receipt metadata for 90 days. Existing live route unchanged.
Validate up to 500 identifiers in a single call — IBAN, VAT, BIC, LEI and ISIN mixed freely. One payment instead of 500, for reconciliation and onboarding runs. Same structural scope as the individual validators.
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. Also callable as GET with the same fields as query parameters.
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. Also callable as GET with the same fields as query parameters.
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. Also callable as GET with the same fields as query parameters.
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. Also callable as GET with the same fields as query parameters.
US demographics by ZIP code (Census ACS 5-year): population, median household income, median age, home value, rent, education, unemployment and poverty.
Check declared citation coverage of up to 64 claims against bounded source and locator inventories. Reject duplicate IDs and dangling references. Coverage is structural, not proof that a source supports a claim.
Deep Research Lite. Re-researches unsupported claims across public sources and returns a receipted result. Requires confirmed: true in the body (otherwise 400, not charged). Async: poll GET /v1/jobs/{id}. $5.00 USDC.
Deep Research Pro. Highest-budget re-research of unsupported claims across public sources, with per-claim verdicts, evidence URLs and a receipt. Requires confirmed: true in the body (otherwise 400, not charged). Async: poll GET /v1/jobs/{id}. $15.00 USDC.
Deep Research Core. Re-researches unsupported claims across public sources and returns per-claim verdicts, evidence URLs and a receipt. Requires confirmed: true in the body (otherwise 400, not charged). Async: poll GET /v1/jobs/{id}. $8.00 USDC.
Extract claims. Splits text into atomic, checkable claims with character spans, grounding_required, claim_type (number|date|quantity|quote|named_entity_fact|comparison|opinion|prediction|other) and check_worthiness (high|medium|low). Strips hedges, resolves pronouns across sentences, and splits compound sentences. $0.05 USDC.
Document parsing: convert office documents (docx, pptx, xlsx, pdf, odt, ods, odp, rtf, epub, csv, doc, ppt) to clean GitHub-Flavored Markdown. Pass a document URL or base64-encoded bytes. Deterministic local Rust converter (Firecrawl anydoc) — fast, typed structure preserved (headings, tables, lists), no OCR for scanned/image-only PDFs.
Convert an array of JSON objects to CSV (nested keys become dot-path columns) or CSV back to JSON. POST { direction: 'json-to-csv'|'csv-to-json', data }.
Compare two lists (emails, IDs, wallets, SKUs...): items in both, only in A, only in B, duplicates within each and union, with counts. Up to 100,000 items per list.
Compute binary Brier score and count-weighted ECE for up to 256 declared held-out score/outcome pairs. Supports probability or percent scores, normalized to probabilities. Equal-width bins use exact rational boundaries: lower inclusive, upper exclusive, final bin includes 1. Empty bins report null means/gaps. No clinical validity claim.
Compare up to 128 expected passage bindings with up to 128 retained descriptors by passage ID, parent document, version hash and chunk hash. Flags omissions, substitutions, repeats and ordering gaps. Public/synthetic metadata only; does not inspect prompts or prove what a model saw or used.
Compare up to 128 expected passage bindings with up to 128 retained descriptors by passage ID, parent document, version hash and chunk hash. Flags omissions, substitutions, repeats and ordering gaps. Public/synthetic metadata only; does not inspect prompts or prove what a model saw or used. New modular adapter: retained result recovery for 24 hours, minimal receipt metadata for 90 days. Existing live route unchanged.
[MCP: fetch_result] Targeted JSONPath extraction (query param mode) from cached context reference.
Convert data between JSON, CSV (auto-detects ; , tab |), YAML, XML and JSON Lines. E.g. a spreadsheet CSV to JSON for an agent, or JSON to CSV for Excel.
Use this service before importing CSV to check data quality: missing cells, duplicate rows, required columns and declared string, integer, number, boolean or date types. Provide raw CSV with unique headers; comma, semicolon and tab delimiters supported. Max 1 MiB UTF-8, 10000 data rows and 100 columns. No URL fetching. Invalid business data returns valid=false.