- Category: web search & research
- Auth: API_KEY
- Composio-managed OAuth available? N/A
- Tools: 5
- Triggers: 0
- Slug:
TAVILY - Version: 20261101_00
- Instant: Supported on the latest version. Support varies by tool.
Tools
Tavily crawl
Tavily crawl
Slug:
TAVILY_CRAWLTool to perform intelligent graph-based website crawling with parallel path exploration and content extraction. Use when you need to traverse and extract content from multiple pages of a website following specific patterns or instructions. Supports depth/breadth controls, domain filtering, and natural language instructions for guided crawling.Input Parameters
Root URL to begin the crawl. Can be provided with or without protocol (e.g., ‘docs.tavily.com’ or ‘https://docs.tavily.com’).
Maximum crawl depth from base URL. Range: 1-5. Depth of 1 means only direct links from the root URL.
Natural language guidance for the crawler to find specific pages or content. Using instructions raises the cost to 2 credits per 10 pages. Example: ‘Find all pages about the Python SDK’.
Extraction level for content: ‘basic’ for standard extraction or ‘advanced’ for deeper analysis.
List of regex patterns for domain filtering. Only URLs matching these patterns will be crawled.
Output
Tavily extract
Tavily extract
Slug:
TAVILY_EXTRACTExtract web page content from specified URLs using Tavily, with optional image extraction and query-based content reranking. Managed Tavily requests support basic extraction depth only.Instant: Supported on the latest version.Instant pricing: $0.008 per 5 successful URL extractions.Discount: 50Input Parameters
User intent for reranking extracted content chunks. Helps prioritize the most relevant extracted content based on the query.
Content format for extraction: ‘markdown’ or ‘text’. Default is ‘markdown’.
Maximum wait time in seconds for the extraction request. Must be between 1.0 and 60.0 seconds. Default is 30.0.
Extraction depth level: ‘basic’ for standard extraction or ‘advanced’ for more in-depth extraction. Default is ‘basic’.
Maximum number of relevant chunks to extract per source. Must be between 1 and 5. Default is 3.
Output
Get Tavily usage
Get Tavily usage
Tavily map website
Tavily map website
Slug:
TAVILY_MAPTool to map a website and discover its pages. Use when you need to scan a website and get a structured list of URLs/pages it contains without extracting full content.Input Parameters
The root URL to begin mapping (e.g., ‘docs.tavily.com’). This is the starting point from which the crawler will discover and map pages.
Maximum number of seconds to wait for the mapping to complete. Range: 10-150. Default is 150.
Natural language directions for the crawler to guide its exploration. Using this parameter raises the cost to 2 credits per 10 pages instead of 1.
List of regex patterns for specific URL paths to include (e.g., ‘/docs/.*’ to only include documentation paths).
List of regex patterns for domain targeting. Only URLs matching these domain patterns will be included.
Output
Tavily search
Tavily search
Slug:
TAVILY_SEARCHSearch the web via Tavily with controls for search depth, result count, and domain filtering. Results can include images, an answer, and raw page content. Managed requests support basic depth only.Instant: Supported on the latest version.Instant pricing: $0.008 per web search.Discount: 50Input Parameters
The search query string to find relevant information online. No native date-filter exists; embed time hints directly in the query string. For broad coverage, issue multiple focused queries rather than one broad query.
Maximum number of search results to return. Large values combined with include_raw_content=true produce very large payloads.
Specifies search depth: ‘basic’ (standard) or ‘advanced’ (in-depth; costs twice the basic price).
If true, attempts to include a direct answer to the query (suitable for factual questions) in search results. The answer field can be null; treat response_data.results array as primary evidence.
A list of domain names (e.g.,
['exclude.com', 'othersite.net']) to exclude from search results; results from these domains will be filtered out.A list of specific domain names (e.g.,
['example.com', 'website.org']) to restrict the search to; only results from these domains are returned.If true, includes raw content from visited websites (e.g., unprocessed HTML or text) in search results. Without this, results may be short snippets that omit critical detail.