Gender-API.com alternatives: price, limits and what we have not measured
Gender-API.com costs €249 a month for one million names, with no public plan above that. What alternatives charge and how to test a switch.
What we measure, what we get wrong, and how to put a gender column on a list of names. Written for the people who have to make the call, not for search engines.
Gender-API.com costs €249 a month for one million names, with no public plan above that. What alternatives charge and how to test a switch.
Namsor was the most accurate gender API we measured and the priciest at volume: $999 a month for 1M names. When an alternative fits better.
Alexa was given to 6,052 American girls in 2015 and 348 in 2024. US birth records 2000–2024 for names that became products, news events or screen characters.
56 common US first names switched sex between 1880 and 2024: 48 went from boys to girls, only 8 the other way. Leslie, Ashley, Morgan, Kyrie and more.
Names that return do so about a century after their first peak: a median of 97 years in the US and 86 in France. Next in line: June, Ruth, Suzanne, Marcel.
In 125 years of French births only 5 common names switched sex, against 56 in the US. Camille is the biggest, and it is now switching back to boys.
We ran common name-validation rules over 600 million official name records. Only A–Z rejects 14% of French people; no spaces rejects 26% of Spaniards.
Greeting people by the usual sex of their first name gets 1 in 47 Americans wrong but only 1 in 1,408 Poles. What a 90% threshold fixes, country by country.
The median living Betty is 78, Brittany 36 and Liam 10. Ages of first names from birth records, with fad names, comeback names and US vs France.
Three working ways to get gender from a first name in Python: gender-guesser, baby-name counts with pandas, and an API, measured on the same 4,610 names.
Inferring gender from names in a study: validate on your data, fix a threshold, report unknowns, check bias by script and country, and what to write in methods.
Counts from ten countries: how many first names are used about equally by both sexes, which ones, and why a name unisex in one country rarely is in the next.
Turn on one setting per API key and the names you send are never written to our request history. What is still recorded, and why a hashed name is not anonymous.
A lead list mixes people, companies and inboxes like info@. NameGender now labels each input personal, organization or role, and only people get a gender.
Free name gender checkers and APIs side by side: lookups without an account, free-account quotas, daily versus monthly limits, and what to test first.
Check whether a first name is male or female in three steps. Real birth-record numbers for Riley, Robin, Kim, Jean and Andrea show when to trust the answer.
A working checklist for integrating a name gender API: deduplicate, batch by country, retry only what can succeed, store the evidence, and set a threshold.
Every NameGender lookup now splits the input into first_name, middle_name and last_name at no extra cost. The rules, real examples, and where splitting fails.
A name gender API estimates the gender tied to a first name from counted records. What it returns, how each answer is reached, and what it cannot tell you.
Measured on 4,610 labelled names from 25 countries: 94% answered, 97% of answers correct, 91% end to end. Results by script, and where the errors come from.
Of 18,076 names given to at least 500 US babies since 1880, 65 are mostly male in one country and mostly female in another. The full list, with counts.
A practical shortlist of name-to-gender APIs, the response fields and workflows that differ, and a benchmark you can run on your own names.
Measured accuracy on the same 991 names, prices at four monthly volumes, and which gender API to pick for which job, including where ours is the wrong choice.
Compare Genderize alternatives by coverage, evidence fields, country handling, spreadsheet workflow and billing instead of relying on a generic feature list.
Coverage on Han names is complete but accuracy is 90.5% — the inverse of the usual pattern. Why pinyin is weaker evidence, and the name-order trap.
Turning an address into a gender is two jobs, and almost every failure is in the first. The exact transform, the confidently wrong cases, and a pre-filter.
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.
Reading the gender field alone discards everything that says whether to believe it. What each response field means and the thresholds behind confidence.
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.
What to measure before you pick a vendor, why a single accuracy percentage tells you nothing, and how to run the same test on all of them — including us.
A reproducible benchmark across 4,610 names, 25 countries and nine writing systems. Thai still answers only half the names, and we publish those numbers too.
With your permission we measure how the site is used and which adverts lead to a sign-up. Both are optional and neither runs until you allow it. Read the cookie policy.