Grokipedia Search API for encyclopedia entries
Search Grokipedia over HTTP and receive the opening of each entry with every result, including the many software and niche topics that have no Wikipedia article.
Endpoint
Results arrive in the same JSON shape as every other engine, so existing parsing continues to work.
The entry name, such as Large language model or TanStack Start.
The link points at the entry page on grokipedia.com.
The snippet is the start of the entry, usually its defining sentence.
Useful for
Definitions / Software topics / Second reference
A second encyclopedia, with wider coverage of software
Set `search_service` to `grokipedia` and the results come from Grokipedia, the English-language encyclopedia from xAI. The endpoint, the authentication, and the response shape are the same as every other engine. Powered by xAI.
Entries Wikipedia does not have
Libraries, SDKs, framework integrations, and recent models often have a Grokipedia entry and no Wikipedia article: TanStack Start, the OpenAI Python SDK, and Cursor’s Composer model all return one.
A definition in the snippet
The `snippet` is the opening of the entry, which usually states what the subject is, so it can ground an answer without a second fetch.
Full entries with references
`crawl_results` returns the whole entry as markdown, including its footnoted references, for the results you choose.
Paging and up to 50 results
`max_results` goes up to 50 and `page` steps through further results. Entries are in English and undated, so `language` and `time_range` do not apply.
What is a Grokipedia search API?
A Grokipedia search API is an HTTP interface that returns Grokipedia entries as structured results. Grokipedia is an English-language encyclopedia published by xAI, and xAI does not offer a public API for searching it. Search1API exposes Grokipedia as one of the search services on its Search endpoint, returning the entry title, the entry link, and the opening of the entry as the snippet, in the same JSON shape it returns for its other engines. Its coverage leans further into software and recent technical topics than Wikipedia does, which makes it a useful second reference: query both, and treat agreement between them as stronger grounding than either alone. Grokipedia content is provided by xAI under the xAI Community License.
Typical workflow
Search Grokipedia over HTTP and receive the opening of each entry with every result, including the many software and niche topics that have no Wikipedia article.
Send an English query with `search_service` set to `grokipedia`.
Use the entry title as the resolved subject and the snippet as the grounding text.
Set `crawl_results` when the workflow needs the full entry and its references.
One request, an entry you can ground on
A single call searches Grokipedia and returns the opening of each entry, so a definition is in hand before deciding whether to read further.
bash
Best for
Defining a library, SDK, or product that has no Wikipedia article.
Cross-checking a Wikipedia definition against a second encyclopedia.
Coding agents that need background on a framework before reading its docs.
RAG pipelines that want a reference layer alongside live web results.
FAQ
Does xAI have an official Grokipedia API?
Not a public one. Search1API returns Grokipedia results through the same Search endpoint and JSON shape as its other engines, so there is no separate client to build or maintain.
Which languages are covered?
Grokipedia entries are in English, so write the query in English. A query in Chinese or Japanese returns poor matches; use `wikipedia`, which follows the query language, or `baidu` for Chinese reference material.
Can I get the full entry text?
Yes. Set `crawl_results` to the number of top results you want fetched, and each page retrieved successfully includes a `content` field with the entry as markdown, references included. Results that cannot be retrieved are returned without `content` and are not charged.
What does a Grokipedia search cost?
One credit per search, and one additional credit for each page retrieved successfully through `crawl_results`. At the base top-up rate of $1 for 1,000 credits, that is $1 per 1,000 searches. Signup includes 100 free credits with no credit card.
Is Grokipedia a reliable source for an AI answer?
Treat it as a reference layer, not a primary source. Some subjects have more than one entry with slightly different titles, and ambiguous words can rank an unexpected entry first. It works best next to `wikipedia` for a second opinion, `arxiv` for research claims, and a web engine for current events.
Can I show Grokipedia results in my product?
Grokipedia content is provided by xAI under the xAI Community License, and some entries are also under CC BY-SA 4.0. The license asks products that display the content to show “Powered by xAI”. Review the license terms for your use.