Skip to navigation

Tavily Search

Tavily Search
Tavily · Research & Search
POST /v1/search

Web search with crawl, extract, and URL mapping for fast, structured retrieval across pages and domains for downstream pipelines.

See Tavily Search pricing and specs or try it in the Playground.

At a glance

FieldValue
Model idtavily-search
Model release date-
Input modalitiesText
Output modalitiesText
Context window-
Weight precision-
Featuresweb_search, crawl, extract, map
Native inferenceNo
NewNo
Supported endpointsPOST /v1/search

Pricing

ChargeSpecRate
Search (Basic/Fast/Ultra-Fast)per search$0.0096
Search (Advanced)per search$0.019
Search (Advanced + Answer)per search$0.029
Extract (Basic)per 5 URLs$0.0096
Extract (Advanced)per 5 URLs$0.019
Crawl/Map (basic)per 10 pages$0.0096
Crawl/Map (with instructions)per 10 pages$0.019

Example request

curl https://api.empiriolabs.ai/v1/search \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H 'Content-Type: application/json' \
-d '{"model": "tavily-search", "query": "latest LLM benchmarks 2026"}'

Parameters

ParameterTypeRequiredDefaultDescription
querystringyes-The natural-language search query.
operation_modeenumno"Search"Search queries the web. Crawl reads pages from a starting URL. Extract returns the content of the given URLs. Map lists the URLs of a site. · Allowed: Search, Crawl, Extract, Map
search_depthenumno"basic"basic = fast and cheap, advanced = deeper crawl per result with full content. · Allowed: basic, advanced, fast, ultra-fast
search_chunks_per_sourcenumberno3Advanced search depth only. Number of relevant content chunks to extract per source. · Range: 1 – 3
search_topicenumno"general"Search topic preset (general, news, finance, etc.). Alias of topic. · Allowed: general, news, finance
include_answerbooleannofalsebasic | advanced | false. Returns a synthesized answer alongside the results.
include_raw_contentbooleannofalseInclude the raw HTML content alongside cleaned text. Search mode only.
include_imagesbooleannofalseInclude image URLs from the search results.
include_image_descriptionsbooleannofalseInclude AI-generated descriptions of returned images. Search mode only. Requires include_images.
include_faviconbooleannofalseInclude the favicon URL of each source. Search mode only.
auto_parametersbooleannofalseLet Tavily auto-pick search_depth and other knobs based on the query. Search mode only.
max_resultsnumberno5Maximum number of results to return (1-20). · Range: 1 – 20
time_rangeenumno-day | week | month | year. Restrict results to this recency window. · Allowed: day, week, month, year
start_datestringno-Only include sources published after this date (YYYY-MM-DD).
end_datestringno-Only include sources published before this date (YYYY-MM-DD).
countrystringno-Two-letter ISO 3166-1 code (US, GB, etc.) for biasing results to a country.
include_domainsstringno-Comma-separated allowlist of domains. Only results from these domains are returned.
exclude_domainsstringno-Comma-separated denylist of domains to filter out.
topicenumno"general"Search topic preset. general (default), news (recent news), or finance (markets / business). Also accepted as search_topic. · Allowed: general, news, finance
daysnumberno-Recency window for the news topic, in days back from today. · Range: 1 – 365
crawl_limitnumberno50Max number of pages to crawl from the starting URL. · Range: 1 – 100
crawl_max_depthnumberno1Maximum link-depth from the starting URL. · Range: 1 – 5
crawl_max_breadthnumberno20Maximum number of links to follow per page. · Range: 1 – 50
crawl_extract_depthenumno"basic"How deeply to extract content from each crawled page. · Allowed: basic, advanced
crawl_formatenumno"markdown"Output format for crawled content: markdown or text. · Allowed: markdown, text
crawl_instructionsstringno-Natural-language instructions for what to look for during crawl.
crawl_chunks_per_sourcenumberno-Number of content chunks to extract from each crawled page. · Range: 1 – 5
crawl_select_pathsstringno-Comma-separated URL paths to include in the crawl.
crawl_exclude_pathsstringno-Comma-separated URL paths to exclude from the crawl.
crawl_select_domainsstringno-Comma-separated domains the crawl is restricted to.
crawl_exclude_domainsstringno-Comma-separated domains the crawl will skip.
crawl_allow_externalbooleannotrueAllow the crawler to follow links to external domains.
crawl_include_imagesbooleannofalseInclude image URLs in the crawl output.
crawl_include_faviconbooleannofalseInclude each crawled page’s favicon URL.
crawl_timeoutnumberno150Crawl timeout in seconds. · Range: 10 – 150
extract_depthenumno"basic"basic | advanced. Advanced extraction reads JavaScript-rendered content. · Allowed: basic, advanced
extract_formatenumno"markdown"Output format for extracted content: markdown or text. · Allowed: markdown, text
extract_querystringno-Natural-language query to filter / focus the extracted content.
extract_chunks_per_sourcenumberno-Number of content chunks to extract from each URL. · Range: 1 – 5
extract_include_imagesbooleannofalseInclude image URLs in the extract output.
extract_include_faviconbooleannofalseInclude the source page’s favicon URL. Extract mode only.
extract_timeoutnumberno10Extract timeout in seconds. · Range: 1 – 60
map_limitnumberno50Max number of URLs to map from the starting site. · Range: 1 – 100
map_depthnumberno1Maximum link-depth from the starting URL. · Range: 1 – 5
map_breadthnumberno20Maximum number of links to follow per page during mapping. · Range: 1 – 50
map_instructionsstringno-Natural-language instructions for what URLs to find during mapping.
map_select_pathsstringno-Comma-separated URL paths the map is restricted to.
map_exclude_pathsstringno-Comma-separated URL paths the map will skip.
map_select_domainsstringno-Comma-separated domains the map is restricted to.
map_exclude_domainsstringno-Comma-separated domains the map will skip.
map_allow_externalbooleannotrueAllow the mapper to follow links to external domains.
map_timeoutnumberno150Map timeout in seconds. · Range: 10 – 150
disable_formattingbooleannofalseReturn the results as JSON instead of formatted Markdown. Search mode only.

Notes

Operations

  • Search, Crawl, Extract, Map

Search depths

  • basic, advanced, fast, ultra-fast

Topics

  • general, news, finance

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/tavily-search.