I Tested DeepSeek’s New Search Api, Here’s How It Ranks and Scores Websites

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 same pattern also shows up in AI Is Merging Paid and Organic Visibility, where the practical question is how the signal becomes visible.

That is a significant release for SEOs. 17, 2026 came alongside an update to its Flash model.

What I Tested

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. Local visibility depends on whether the details across pages, profiles, categories, reviews, photos, and service descriptions reinforce the same answer for a specific location based query.

The operational question is whether the public business data is complete enough to support the query. Hours, categories, services, reviews, photos, and page content need to reinforce each other so Google can understand the business in a specific situation, not only as a generic listing.

DeepSeek Gives You 2 Scores

Each search result includes two fields worth paying attention to: These definitions come from the Search API reference. The authority tier is DeepSeek's own assessment, and the documentation describes it as a property of the page. Across. The search implication is whether the section improves the evidence around the page, not simply whether it adds more wording. Clear entities, crawlable structure, internal links, and useful context are what make the topic easier to evaluate.

The useful check is whether this improves the system behind search performance, not only the words on the page. Internal links, crawlable content, clear entities, current evidence, and a sensible page structure all help the recommendation become easier to trust.

Authority Looked Tied To The Host. Mine Was 1

Across all 4,322 results in the run, authority tiers -1 and 0 never appeared. The distribution looked like this: Higher authority tiers came with higher median rerank scores in this sample. That doesn't isolate the effect of authority from. For search teams, the important part is not the headline movement by itself. It is whether the shift changes which communities, forums, video surfaces, or publisher pages now satisfy the query better than the old ranking pattern.

I Lost My Own Tool Queries To Registries And App Stores (Lol)

I ran six target queries with count=50 from the UAE. Package registries, app stores, and marketplace listings did well on these tool queries. PyPI, npm, Apify, the Chrome Web Store, WordPress.org, and GitHub were the kinds of hosts. The search implication is whether the section improves the evidence around the page, not simply whether it adds more wording. Clear entities, crawlable structure, internal links, and useful context are what make the topic easier to evaluate.

The Spam Filtering Still Let Some Questionable Stuff Through

DeepSeek explicitly says its engine filters SEO spam, GEO manipulation, and low quality AI content. I wanted to see how that claim lined up with the results. I also saw self published "frameworks" on zenodo.org receive authority four and. The search implication is whether the section improves the evidence around the page, not simply whether it adds more wording. Clear entities, crawlable structure, internal links, and useful context are what make the topic easier to evaluate.

How To Run The Same Kind Of Search

Here is a request using an API key stored in an environment variable: Search and Fetch each cost $0.75 per 1,000 successful requests. Under the billing rules, failed requests, empty search results, and timeouts are not billed. Returning. The search implication is whether the section improves the evidence around the page, not simply whether it adds more wording. Clear entities, crawlable structure, internal links, and useful context are what make the topic easier to evaluate.

3 Things To Account For When Testing

Introduction 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. That is. For search teams, the important part is not the headline movement by itself. It is whether the shift changes which communities, forums, video surfaces, or publisher pages now satisfy the query better than the old ranking pattern.

1. Set Your Localization

Leaving out localization produced the same results as specifying a UAE IP across all six target queries. I was calling from Dubai, which is consistent with DeepSeek using the caller's IP as the default. Set this field explicitly to an IP. Local visibility depends on whether the details across pages, profiles, categories, reviews, photos, and service descriptions reinforce the same answer for a specific location based query.

2. The Original Question Made Very Little Difference

The ori_question field lets you supply the user's original question alongside the search query. DeepSeek says this can improve query understanding. Across my six queries, it changed the rerank score for only zero to two of the 50 results. The search implication is whether the section improves the evidence around the page, not simply whether it adds more wording. Clear entities, crawlable structure, internal links, and useful context are what make the topic easier to evaluate.

3. Date Filters Removed Every Undated Result

The after: and before: operators produced zero date violations across four queries. They also removed every undated page. 11% of the unfiltered results had date: null, and those URLs disappeared when a date filter was applied. That. The search implication is whether the section improves the evidence around the page, not simply whether it adds more wording. Clear entities, crawlable structure, internal links, and useful context are what make the topic easier to evaluate.

The risk is usually hidden in the execution layer. A page can look fine to a human and still fail for an automated visitor if the form, call to action, rendering path, or confirmation step is not accessible enough for the agent to complete the task.

What the visibility signal actually changes

What the visibility signal actually changes: i Tested DeepSeek’s New Search Api, Here’s How It Ranks and Scores Websites: the Practical Angle should be treated as a visibility signal, not a standalone headline. Introduction 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. That is a significant. This connects with We Earned 1 when the same signal needs a clearer operating decision. A useful companion note is So Build What It Can Read, because it looks at a nearby part of the same system.

What the visibility signal actually changes: the practical question is whether the page, brand evidence, and surrounding content make the answer easier to trust. If that support is weak, search systems can still understand the topic but fail to connect it confidently to the brand.

What the visibility signal actually changes: that is why the response should begin with an audit of the evidence already on the site before creating a new asset. The fastest improvement is often a clearer page, a better internal link, or a stronger explanation of why the brand belongs in the answer.

Where the evidence needs to be tested

Where the evidence needs to be tested: a single study or ranking observation should not become a strategy by itself. It should become a diagnostic prompt: which source is being trusted, which query pattern is affected, and which part of the site would make that trust easier to earn?

Where the evidence needs to be tested: that keeps the response grounded. The goal is to improve the evidence chain around the topic rather than publish another summary that repeats what every other page already says.

Where the evidence needs to be tested: the important distinction is between a useful signal and a fashionable talking point. A useful signal changes the brief, the page structure, the linking plan, or the measurement view.