genderize.io

What It Is

Genderize.io is a name-based gender prediction API: you submit a name, and it returns a predicted gender, probability score, and sample count. It belongs to the same product suite as Agify.io and Nationalize.io, sharing around 1 billion data rows, the same API key, and the same subscription. Together, they can be used to infer gender, age, and nationality. Its purpose is not identity verification, but demographic enrichment for bulk data analysis.

Core Capabilities and Ecosystem

From a developer tooling perspective, Genderize.io has a straightforward API design. You can call it via api.genderize.io?name=anna, and it also supports batch requests of up to 10 names. It supports full name parsing, diacritics, and non-Latin characters, and can use an ISO country parameter to restrict results by region; for example, the same name may have different gender distributions in Denmark and the United States. In terms of ecosystem, community SDKs cover Python, Ruby, Go, JavaScript, PHP, Java, C#, R, Scala, and more, with a list of 23 libraries. The official site also provides a Spreadsheet tool, no-code integrations for n8n/Pipedream/Zapier/Make, and a hosted MCP server for MCP clients such as Claude, Cursor, and ChatGPT.

Pricing and Documentation

The free plan includes 2,500 names per month and does not require a credit card. Paid plans start at $20/month, with multiple usage tiers and cancellation at any time. The main materials reference an API reference, MCP docs, setup guide, FAQ, Our Data, and case studies, making the documentation entry points fairly complete. They also explain how probability should be interpreted, how country_id works, batch requests, and the logic of returning null when there is no match.

Pros and Cons

The advantages are that it is quick to get started with, covers many countries and regions, is suitable for high-volume batch processing, and already has many use cases in academia, media, customer analytics, and similar scenarios. The drawbacks are equally clear: the predictions are statistical probabilities and are not suitable for sensitive individual-level decisions. Performance varies across cultural naming conventions, and the main examples explicitly mention fairness issues such as potentially higher error rates for Chinese pinyin names and relatively low representation of Chinese data. The service itself does not state that it is open source or self-hostable, and most SDKs are community-maintained.

Who It’s For and Access from China

Genderize.io is suitable for data scientists, researchers, journalists, and CRM/marketing analytics teams that need gender distribution analysis at an aggregate level. The source material does not specify access conditions from China, nor does it disclose payment methods. If you are processing Chinese names, it is advisable to first evaluate error rates using your own labeled samples, and to consider Chinese-name-specific datasets or local rules/models as alternatives or complements.