Browse indexable data x402 offerings, including provider, method, and service details.
990 indexable offerings in this category.
Use to flag outliers in any series ($0.01): send value and reference values; get a 0-100 anomaly score, the z-score, severity (NORMAL, LOW, MEDIUM, HIGH, EXTREME) and direction (ABOVE/BELOW). Fixed statistical thresholds, no AI and no data fetched; a score, not a probability.
Use to check whether two series move together ($0.01), e.g. returns of two assets or a signal versus outcomes: send equal-length x and y; get Pearson r (default) or Spearman rank correlation, r-squared and direction. Deterministic decimal math on your numbers, nothing fetched.
Use to turn evidence quality into one auditable 0-100 confidence ($0.01): send factors such as sample size, data freshness, source agreement and signal consistency (each 0-100, weighted); get the confidence, a band and the weakest factor. A transparent weighted mean, not AI confidence.
Use to rank a value against a dataset ($0.01), e.g. today's volume versus the last 90 days: send value and values; get its 0-100 percentile rank with counts below, equal and above. Methods LINEAR (default, interpolated), MIDRANK and AT_OR_BELOW. Deterministic, no data fetched.
A/B test significance with a two-proportion z-test: observed lift, z-score, two-sided p-value, confidence interval on the lift, minimum detectable effect, and sample-size sufficiency. Pure computation over your inputs.
Schema-driven extraction: fill YOUR JSON schema from any URL. Hybrid LLM + deterministic canonicalization. $0.03/call.
PDF facts before you pay for parsing: page count, metadata, per-page text volume, scanned-or-not estimate. $0.001/call.
Schema-driven extraction: fill YOUR JSON schema from any URL. Hybrid LLM + deterministic canonicalization. $0.03/call.
Deduplicate a list of names or addresses into clusters of likely duplicates. Blocks by similarity key then confirms pairwise inside each block, returning clusters with a canonical representative plus a summary of input, cluster and duplicate counts. Similarity indicators, not authoritative identity resolution.
Fuzzy-match two names or addresses and return a 0-100 similarity score with a match decision. Normalizes legal forms, business stop-words, person titles and address abbreviations BEFORE the fuzzy compare, then fuses token, prefix, phonetic and edit similarity. Returns the score, the per-component scores, the normalized forms and is_match. Similarity indicators, not authoritative identity resolution.
Standardize a company name, person name or address to a canonical form. Canonicalises legal forms, drops business stop-words, strips person titles and suffixes and folds address abbreviations. Returns the canonical form, the tokens and the rules that were applied. Indicators, not authoritative identity resolution.
Consolidate up to 128 cut rows by material and exact converted length in metres, summing integer quantities and total lengths without floating-point arithmetic. Supports mm/cm/m and four material classes. No kerf, stock nesting, waste optimization or fabrication certification. New modular adapter: retained result recovery for 24 hours, minimal receipt metadata for 90 days. Existing live route unchanged.
Consolidate up to 128 cut rows by material and exact converted length in metres, summing integer quantities and total lengths without floating-point arithmetic. Supports mm/cm/m and four material classes. No kerf, stock nesting, waste optimization or fabrication certification.
Reconcile required qualification tests with supplied pass/fail/not-run evidence records. List declared passes, failures and gaps; no material certification.
Convert any public webpage into clean JSON that matches your schema.
For agents reviewing shot-count results: return probabilities and binomial confidence intervals with the interval method and independence assumptions.
Compare Cross-reference subtitle cues with contained source words and flag label mismatch. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller su…
Compare Index subtitle display gaps for caption coverage review. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authen…
Takes two documents, by URL, inline base64 or raw text, extracts the text of each and compares them. Paragraphs are the unit: the answer lists every block that was removed, added, or kept but reworde…
Compare Timestamped source search for consent vocabulary, no legal conclusion; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline…
Compare Timestamped source search for loading discussion wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller su…
Compare Flag fast, short and text-heavy cues for explicit editorial review. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is n…
Compare Locate caller-specified literal redaction strings; no semantic PII detection. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplie…
Compare Index subtitle display gaps for caption coverage review. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.