Back to Directory
T

Tavily API via AIsa

Other
Unified API documentation for Tavily endpoints including Search, Extract, Crawl, and Map.

About Tavily API via AIsa

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

Service details

Service Id
21b0953b-d5bb-4c2b-88f6-1628aedbb41a
Service origin
https://api.aisa.one
ListedSeptember 24, 2026, 6:45 PM
Last checkedSeptember 24, 2026, 8:07 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/tavily/crawl

Graph-based website traversal tool using Tavily Crawl.

Walk a site from a root `url` and return the content of the pages it finds. Steer it with natural-language `instructions` plus regex path and domain filters, and bound it with `max_depth`, `max_breadth` and `limit`. Returns `base_url` and `results[]` with `url` and `raw_content`. Measured at about 4.5 seconds for a 3-page limit; cost and time grow with the bounds you set, so set them. Use it for broad coverage of one site — documentation, a catalogue, a competitor's blog. It answers synchronously, which `post_firecrawl_crawl` does not: that one runs as a background job and suits crawls too large to wait on. For a handful of known pages `post_tavily_extract` is far cheaper; to size a site before paying to crawl it, run `post_tavily_map` first.Price unavailableThe operation requires declared authentication; API keys, bearer tokens and other schemes are not evidence of AEP support.
POST/tavily/extract

Extract web page content from specified URLs using Tavily Extract.

Fetch clean, parsed content for URLs you already have — from a search result, a sitemap, or a user. `urls` is required and takes several at once. Returns `results[]` with `url`, `title`, `raw_content` and `images`, plus a `failed_results[]` array — **read that one**, because a page that could not be fetched is reported there rather than raising an error. Choose `format` (markdown or text) and `extract_depth`. Measured at about 1 second for one page. Use this instead of `post_tavily_search` whenever you can already name the pages; searching for pages you can name costs more and may not return them. For a long list that can wait, `post_firecrawl_batch_scrape` runs it as a background job. To discover the URLs of a whole site first, use `post_tavily_map`.Price unavailableThe operation requires declared authentication; API keys, bearer tokens and other schemes are not evidence of AEP support.
POST/tavily/map

Generate comprehensive site maps using Tavily Map.

List a site's URLs from a root `url` without fetching any page content. Steer it with natural-language `instructions` and regex `select_paths` / `exclude_paths` / `select_domains` filters. Returns `base_url` and `results` — **a flat array of URL strings, not objects** — with `response_time` and `request_id`. Fast and cheap: measured at about 1.5 seconds. Use it to size a site before committing to a crawl, then fetch only the parts that matter with `post_tavily_extract`. When you want the content rather than the shape, `post_tavily_crawl` does both in one call.Price unavailableThe operation requires declared authentication; API keys, bearer tokens and other schemes are not evidence of AEP support.
POST/tavily/search

Execute a search query using Tavily Search.

Search the web and get back ranked results with the page text already extracted, so there is no second call to fetch content. `query` is required. Returns `results[]` with `url`, `title`, `content` (the extracted excerpt), `score` and optionally `raw_content`, alongside `query`, `images`, `response_time` and `request_id`; set `include_answer` to also get a one-paragraph `answer`. Filter with `topic` (general/news/finance), `time_range` or explicit `start_date`/`end_date`, and trade cost against depth with `search_depth`. Measured at roughly 6 seconds for 2 results. This is the default choice for open-web research, and the only search here that returns ranked results and page text in one call. Reach past it when: you already know the URLs — `post_tavily_extract` is cheaper and exact; the query is a description rather than keywords — `post_exa_search` matches on meaning; you want a written answer rather than a list to iterate — `post_perplexity_sonar`; you want peer-reviewed papers — `post_scholar_search_schol…Price unavailableThe operation requires declared authentication; API keys, bearer tokens and other schemes are not evidence of AEP support.