Tavily Search
Tavily Search
Tool
tavily_crawl
Crawl a website starting from a URL. Extracts content from pages with configurable depth and breadth.
Pricing
Per call
$0.02
Model
flat
Pay only for what you use. No subscriptions.
Inputs
instructions
stringselect_domains
arrayinclude_favicon
booleanselect_paths
arraymax_depth
integerlimit
integerformat
stringextract_depth
stringallow_external
booleanurl *
stringmax_breadth
integerTry It
API
MCP Config
Input Parameters
Natural language instructions for the crawler. Instructions specify which types of pages the crawler should return.
Regex patterns to restrict crawling to specific domains or subdomains (e.g., ^docs\.example\.com$)
Regex patterns to select only URLs with specific path patterns (e.g., /docs/.*, /api/v1.*)
Max depth of the crawl. Defines how far from the base URL the crawler can explore.
Total number of links the crawler will process before stopping
markdown
The format of the extracted web page content. markdown returns content in markdown format. text returns plain text and may increase latency.
basic
Advanced extraction retrieves more data, including tables and embedded content, with higher success but may increase latency
The root URL to begin the crawl
Max number of links to follow per level of the tree (i.e., per page)