Check gender from a name
Enter one name and see the evidence behind the result. The checker reports probability, sample size and source instead of hiding uncertainty behind a single label.
100 free credits every day. No card.
Try the name checker
No signup. Add a country only when it belongs to the record.
Read the result as evidence, not identity
A name can carry a statistical association without describing an individual. The result tells you how a name appeared in aggregated records, not how the person identifies. Keep that distinction in any CRM field, report or personalisation rule built from the answer.
The probability is the dominant share in the matched data. The sample size tells you how much counted evidence sits behind that share, while the source identifies the lookup path. A high percentage based on a small sample should not be treated like the same percentage based on thousands of observations.
Unknown is a valid outcome. It means the available data did not support a useful answer. Preserving unknown as its own value is safer than silently assigning a default and makes gaps in coverage visible when you audit a dataset later.
Country changes the question
Names travel. Andrea is commonly male in Italy and commonly female in several other markets. Kim, Jean and Noa also change distribution by country. Add a two-letter country code when your record contains one so the lookup uses the relevant population rather than a blended global result.
Do not infer country from an email domain or the current location of a customer unless that is genuinely the population you need to measure. A billing country, declared market or source-system country is a clearer signal. If there is no reliable hint, leave the field empty and retain the returned probability.
The checker accepts a single name for quick inspection. For repeatable application logic, use the API; for a customer list, upload the spreadsheet so column mapping, deduplication and output fields stay visible.
Choose a threshold before using the answer
A threshold belongs to the use case. A low-risk aggregate report can retain lower-confidence results as long as unknown remains separate. A visible salutation should use a stricter threshold and a neutral fallback. Decisions in employment, credit, health, insurance or eligibility should not be made from name-based inference at all.
Write the threshold into the process rather than applying it by eye. For example, accept only probability values of 90 or more for optional greeting personalisation, and use a neutral greeting for everything else. Store the source and sample fields next to the result so the decision can be reproduced after the data changes.
One successful example does not validate a market. Test a labelled sample drawn from your real audience, including ambiguous names, multiple scripts and deliberate nonsense. Measure coverage, accuracy when answered and end-to-end accuracy separately before putting the checker into a workflow.
Questions
Is this checker free?
Yes. The public checker requires no account and is rate-limited to prevent automated use. A free API account is available for integration testing.
Does the result identify a person’s gender?
No. It reports a statistical association for a name in aggregated data. It cannot know an individual’s identity.
Why did the checker return unknown?
The input may be absent, ambiguous, a company name, or unsupported in the available data. Unknown is returned instead of forcing an answer.
Can I check an Excel file?
Yes. Use the batch upload in the dashboard for CSV or Excel files and download the enriched result.
Related pages
How gender inference from a name works, when country matters, what probability and sample size mean, and how to handle ambiguous or unknown results.
Every name lookup returns a probability, a sample size and a confidence tier. What each one measures, how the tiers are set, and where to put your threshold.
Upload a CSV or XLSX name list and get a gender column back, with confidence fields, automatic deduplication and the cost shown before charging.
Reading the gender field alone discards everything that says whether to believe it. What each response field means and the thresholds behind confidence.
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.