DeepSeek opened its search API with authority scores and a promise to filter SEO and GEO spam. I spent $0.08 testing what it actually returns.

DeepSeek has opened access to its own search engine through a public Search and Fetch API. It returns an authority score for every result and says it filters out SEO spam, GEO manipulation, and low-quality AI content.

The announcement on Oct. 17, 2026 came alongside an update to its Flash model. DeepSeek says the search engine already powers search on its website and through its API, indexes hundreds of billions of pages and handles hundreds of millions of searches a day.

We can now query that system directly, inspect the sources it returns, and see some of the scores attached to them. That gives us something concrete to investigate before an AI model turns those sources into an answer.

Naturally, I wanted to see what it thought of my site. And whether the spam filtering held up.

My site came back with an authority score of 1. Spam PDFs on government and university hosts came back with authority 4. The Fetch API also presented itself as Firefox from Hong Kong and returned content from URLs disallowed by robots.txt.

I ran 110 calls on Oct. 17, 2026 from Dubai: 93 Search calls and 17 Fetch calls. Around 103 were billable under the documentation’s billing rule, costing approximately $0.08.

The tests covered score distributions, authority across different hosts, six queries related to my own tools and research, localization, date filters, and fetch behavior.

Source link