Back to Directory
Scholar

Scholar

Web Search
Search scholarly and web sources and request explanations of research results.
Available through AIsa

About Scholar

Review the Service identity, supported languages, protocol versions, and source metadata discovered by the directory.

Service details

Service Id
47c116ee-6878-4305-9007-55c5cc5a7cff
Service origin
https://api.aisa.one
ListedNovember 15, 2026, 10:28 AM
Last checkedNovember 15, 2026, 2:51 PM

Protocol details

SourceOpenAPI

Endpoints

Endpoint details are saved from the OpenAPI document. Authentication requirements and prices are advertised information, not a verified payment or access guarantee. The document may contain additional endpoints.Open OpenAPI document
POST/apis/v1/scholar/search/explain

Explain Search Results

Explain a result set you already fetched. Unlike the three search endpoints this one takes a **JSON body**: `search_id` (required — the `id` returned by `post_scholar_search_web`, `post_scholar_search_scholar` or `post_scholar_search_mixed`), plus `detail_level` (BRIEF / MODERATE / DETAILED), `language`, and `response_mode`. ⚠️ Use `response_mode: NON_STREAMING`. It returns `{"message": "…"}` as JSON, measured at about 2 KB. The COMPLETE and INCREMENTAL modes emit server-sent events in which **each event repeats the whole answer so far** — the identical explanation measured 177 KB that way, roughly 90 times larger, and a tool call cannot consume a stream incrementally anyway. It only ever explains an existing search; it cannot run one.Authentication required.
POST/apis/v1/scholar/search/mixed

Search Mixed Content

Search the web and academic sources together, for questions that straddle both. ⚠️ Parameters go in the **query string**: `query` (required), `max_num_results`, `as_ylo`/`as_yhi`. Returns a search `id` and `results[]`; **the entry shape varies by source** — every result has `title`, `link` and `snippet`, and academic ones additionally carry `authors` and `number_of_citations`, so treat those two as optional rather than assuming they are there. Measured at about 3 seconds. Use it when you do not know in advance which kind of source will answer. When you do, `post_scholar_search_web` or `post_scholar_search_scholar` is more predictable. Keep the `id` for `post_scholar_search_explain`.Authentication required.
POST/apis/v1/scholar/search/scholar

Search Scholarly Articles

Search academic literature. ⚠️ Parameters go in the **query string**, not a body: `query` (required), `max_num_results`, and `as_ylo`/`as_yhi` to bound publication years. Returns a search `id` and `results[]` with `title`, `link`, `snippet`, `authors` and `number_of_citations` — that last field is what a general web search cannot give you. Measured at under 2 seconds. Use it when the question calls for peer-reviewed sources or when citation counts matter. For current events and product pages a general engine is better: `post_tavily_search`. To cover both at once, `post_scholar_search_mixed`. Keep the `id` for `post_scholar_search_explain`.Authentication required.
POST/apis/v1/scholar/search/web

Search Web Content

Search the open web and get back a lean result list. ⚠️ Despite being a POST, parameters go in the **query string** — `query` (required), `max_num_results` (default 10, max 100), and `as_ylo`/`as_yhi` for a year range. A JSON body is not accepted. Returns a search `id` and `results[]` carrying only `title`, `link` and `snippet`. Measured at about 4 seconds for a roughly 600-byte response. Its virtue is how little it returns, which suits an agent that only needs to know what exists. It gives you no page text — if you need the content, `post_tavily_search` returns it in the same call. Keep the `id`: it is what `post_scholar_search_explain` needs.Authentication required.