Customer and lead gender enrichment
Take the list you already have — a CRM export, a signup table, a lead file — and append gender with the evidence attached, so downstream you can tell a measured answer from an attested one.
100 free credits every day. No card.
Two ways in, same fields out
Upload a CSV or XLSX and get the file back with columns appended, or call the API from wherever the records already live. The response fields are identical either way, so a batch backfill and a live signup hook do not disagree with each other.
For an existing database, the usual shape is one bulk file to backfill history and an API call on new records. The bulk path deduplicates before lookup, which matters more than it sounds: a 200,000-row customer list typically contains around 16,000 unique first names.
Enrich on what you have, not what you wish you had
Most CRM tables do not have a clean first-name column. Four input types cover what is actually in the row:
Where a record offers more than one of these, prefer the one further up the list. Each step down adds an extraction stage that can fail quietly, and no confidence field can see an extraction failure — it reports on the classification of whatever string was extracted, correct or not.
Whichever you use, keep the name field from the response alongside the result. It records what was actually looked up, which is the difference between auditing your pipeline later and guessing about it.
| You have | Endpoint | Note |
|---|---|---|
| A first name | /api | The strongest signal |
| A full name | /api | Titles and initials stripped; check the name field for what was extracted |
| An email address | /api/email | Filter role addresses first |
| A username or handle | /api/username | camelCase and trailing digits normalised |
The country column is worth more than the vendor
If your records carry a country — billing address, phone prefix, signup IP, storefront — map it into the request. Andrea is male in Italy and female in Germany; Jean is male in France and female in the United States. A country-blind enrichment gets those systematically wrong for one national segment while the aggregate error rate still looks fine.
This single column moves accuracy more than switching providers does.
Credits do not expire
Enrichment is bursty by nature: a large backfill, then a trickle. Monthly plans price that badly, because you pay twelve months to use four. Credits here are bought once and stay bought, and unresolved names are the cheapest part of the bill because duplicates are collapsed before lookup.
Questions
What happens to rows we cannot resolve?
They come back with an empty gender and confidence: unknown. Keep them as their own segment. Imputing them to the majority class does not remove the bias, it hides it in your totals — and the unresolved rows cluster by country and script rather than being random.
Is this GDPR-compatible?
Inferred gender is personal data and your lawful basis is yours to establish. On our side, the data processing agreement sets out the processor terms, and the KVKK notice covers the Turkish regime.
Can we test before buying?
Yes, and you should — on your own list rather than a demo list. The free tier is enough to enrich a representative sample and check the error rate per segment.
Do you bill for duplicates?
Bulk files deduplicate before lookup, so repeated names in a file are resolved once.
Related pages
Upload a CSV or XLSX name list and get a gender column back, with confidence fields, automatic deduplication and the cost shown before charging.
Detect gender from an email address. The exact local-part transform, the role addresses that produce confidently wrong answers, and the pre-filter to run first.
What is actually in the name-to-gender dataset: seven counted national registries, WGND 2.0 for the rest, versioned snapshots and a per-answer source field.
A walkthrough for analysts: upload a name list, pick the right columns, read the confidence fields, and decide what to do with the rows that come back empty.
Some ordinary names flip gender across borders, and the error is systematic rather than random. What the country parameter does, and where the data comes from.
Check it against your own list
Every number on this page is reproducible with a free key. If your data breaks it, that is the more interesting result.