Marketplace/tavily/tavily_search

tavily/tavily_search

Search the live web for any current information — general lookups, research, fact-checks, or the latest news and headlines — returning relevant snippets with source links, structured for direct use by agents and RAG pipelines. Refine results with time range or exact dates, country boosting, domain include/exclude filters, result count, search depth, and optional raw page content or related images.

by Faro

10 credits / call ($0.01)
charged on success

What it does

Searches the live web for a query and returns relevant snippets with source URLs, structured and chunked so an agent or RAG pipeline can use the output directly. Results can be refined with time range, date filters, country targeting, domain include and exclude lists, result count, and faster or deeper search modes.

Primary use cases

  • AI agents grounding answers in fresh web context with built-in citations, reducing hallucination on questions about current events or recent product changes.
  • RAG and assistant pipelines that need clean, deduplicated snippets instead of raw HTML to feed into an LLM context window.
  • Researchers and analysts pulling targeted information from a curated set of trusted domains while excluding low-quality sources.
  • Developers building production agents that need predictable latency and safeguards against prompt injection from scraped content.

Why use this tool

Tavily is built specifically for agent and RAG workloads, with p50 latency around 180ms, content that is pre-chunked for model consumption, and safeguards that block PII leakage, prompt injection, and known malicious sources. The domain include and exclude lists are particularly useful for keeping retrieval scoped to authoritative sites, and the deeper search mode trades latency for broader coverage when accuracy matters more than speed.

Good to know

Time range and explicit date filters control freshness, country targeting localizes results, and the search mode parameter lets callers pick between fast lookups and more thorough multi-source passes. Domain include and exclude lists compose, which makes it easy to lock retrieval to a known good corpus.

Parameters

querystringrequired

Search query

topicstringoptionaldefault: "general"

The category of the search. This will determine which of our agents will be used for the search

countrystringoptionaldefault: ""

Boost search results from a specific country. Must be a full country name (e.g., 'United States', 'Japan', 'Germany'). ISO country codes (e.g., 'us', 'jp') are not supported. Available only if topic is general. See https://docs.tavily.com/documentation/api-reference/search for the full list of supported countries.

end_datestringoptionaldefault: ""

Will return all results before the specified end date. Required to be written in the format YYYY-MM-DD

start_datestringoptionaldefault: ""

Will return all results after the specified start date. Required to be written in the format YYYY-MM-DD.

time_rangeoptionaldefault: null

The time range back from the current date to include in the search results

exact_matchoptionaldefault: null

Only return results containing the exact phrase(s) in quotes in your query

max_resultsintegeroptionaldefault: 5

The maximum number of search results to return

search_depthstringoptionaldefault: "basic"

The depth of the search. 'basic' for generic results, 'advanced' for more thorough search, 'fast' for optimized low latency with high relevance, 'ultra-fast' for prioritizing latency above all else

include_imagesbooleanoptionaldefault: false

Include a list of query-related images in the response

exclude_domainsarrayoptionaldefault: []

List of domains to specifically exclude, if the user asks to exclude a domain set this to the domain of the site

include_domainsarrayoptionaldefault: []

A list of domains to specifically include in the search results, if the user asks to search on specific sites set this to the domain of the site

include_faviconbooleanoptionaldefault: false

Whether to include the favicon URL for each result

include_raw_contentbooleanoptionaldefault: false

Include the cleaned and parsed HTML content of each search result

include_image_descriptionsbooleanoptionaldefault: false

Include a list of query-related images and their descriptions in the response

tavily/tavily_search — Faro