DeepSeek opened its in-house search engine to builders on Oct. 17, and the corporate’s changelog says the engine filters website positioning spam, “GEO manipulation,” and low-quality AI-generated content material.
Every consequence from the brand new Search API contains an authority tier for the web page and a relevance rating, and the API accepts web site: queries that restrict outcomes to at least one area.
What DeepSeek Says About Its Engine
DeepSeek’s changelog says its in-house engine handles search on its web site and in its API, indexes tons of of billions of internet pages, and takes in tons of of hundreds of thousands of search requests a day from world wide.
GEO (generative engine optimization) is whenever you form your content material to be cited by AI reply engines. DeepSeek’s changelog states that they credit score strict detection because the supply of filtering; nevertheless, it has not outlined what GEO manipulation is or described how their detection course of operates. On Could 15, Google mentioned “our spam insurance policies additionally apply to generative AI responses in Google Search.”
The privateness coverage of DeepSeek was final revised Feb. 10, which states that the corporate integrates “third-party APIs to supply search companies” and shares customers’ enter key phrases with these corporations. A Chinese language-based search API firm referred to as Bocha states they’re the official internet search provider of DeepSeek within the buyer part of a GitHub README for certainly one of their merchandise. DeepSeek doesn’t reference Bocha of their launch pages. The changelog and the privateness coverage don’t state if any internet search queries are nonetheless despatched to a 3rd celebration service. Dan Petrovic from DEJAN referenced each the privateness coverage and the GitHub README in his submit in regards to the DeepSeek launch.
What The Search API Returns
Every Search API consequence incorporates an authority subject; authority fields vary from 0 to 4 with -1 being unknown. In accordance with DeepSeek’s API reference, pages with tiers of three+ are described as “extremely authoritative” sources.
The rerank rating (one other subject) is a scale of 0-3 and incorporates indicators that embody relevance, authority and freshness. A rerank rating of 1.5+ is taken into account prime quality. The information and the reference don’t clarify how a web page receives its tier or rating.
Every consequence additionally comes with a snippet for show, sometimes 100 to 200 characters, and a abstract meant for a mannequin to learn, sometimes 600 to 800 characters. Web page content material comes again too when a request asks for it and the content material is out there. Queries might be restricted with web site: and filtered by language and date printed.
Search and Fetch every price $0.75 per 1,000 profitable requests. Searches that return no outcomes aren’t billed, and requesting 50 outcomes prices the identical as requesting only one.
What DeepSeek’s Pages Say About Crawling
DeepSeek’s Fetch API was launched with Search. Fetch offers a single Markdown web page and “is topic to the goal web site’s availability and entry insurance policies,” as per the information.
In accordance with the EU abstract of the information used to coach DeepSeek-V4, the crawler is “designed to respect robots.txt directions and different customary internet protocols, the place relevant.” Nevertheless, the abstract doesn’t determine which crawler this refers to.
Moreover, not one of the launch pages (the information, API references, changelog and announcement) present identification of a crawler for the search index nor do they supply info on what consumer agent Fetch makes use of.
Along with offering details about a number of crawlers, the Recognized Brokers bot listing lists a DeepSeekBot consumer agent and describes it as an AI coaching knowledge crawler.
Why This Issues
With a funded DeepSeek API account, particular person web site: searches are underneath $0.01. Every web site: search can return as much as 50 pages out of your web site; every web page has each an authority tier and a relevance rating for that question. In case you see a lacking consequence, it might be as a result of the web page was both outdoors the index or caught by filters described in DeepSeek’s changelog, or as a result of it was excluded for another cause; neither the consumer information nor the API reference offers a way to determine this out.
Robots.txt guidelines supposed to dam DeepSeekBot are focused in opposition to a crawler that the Recognized Brokers bot listing describes as being related to coaching knowledge. It doesn’t seem from DeepSeek’s preliminary launch pages if such a rule will have an effect on what’s included in DeepSeek’s search index.
Wanting Forward
In case you use Claude Code, Codex, or DeepSeek Harness with the DeepSeek API, your server-side searches and web page fetches are already dealt with via the Search and Fetch APIs without charge. Billing for these server-side calls will start on Oct. 31 at 16:00 UTC (midday ET).
Watch DeepSeek’s docs for a definition of GEO manipulation, particulars on how tiers are set, and a named crawler for the index.
