Skip to main content
Billing note Billed per search: 19 credits for basic/fast/ultra-fast, 38 for advanced. With auto_parameters=true, 38 credits are reserved (Tavily may pick advanced) and the difference is refunded when Tavily reports it used a basic search.
TavilyFastHigh

Tavily Search

Real-time web search built for LLMs and agents - returns ranked results with relevant content snippets, an optional LLM-generated answer, raw page content, images and domain/date filters. 19 credits per basic search, 38 per advanced search.

19 credits
per search (basic/fast/ultra-fast; 38 for advanced)
Results ranked for LLM grounding, with relevant content chunks per source
Optional LLM-generated answer (basic or advanced)
Full page content as markdown or text with include_raw_content
general / news / finance topics, time range and date filters
Include or exclude domains, country and language boosting

Run it right now

Test this model instantly in the Console Playground — no code required

Sign in to try

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

Quick Start

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "tavily/search",
  "input": {
    "query": "latest AI video generation models 2026",
    "search_depth": "basic",
    "max_results": 5,
    "include_answer": "basic"
  }
}'

Parameters

ParameterTypeRequiredDefaultDescription
querystringYes-The search query. Write it in the language you want results in.
search_depthstringNobasicbasic is a balanced generic search; advanced returns the most relevant content chunks at higher latency (2x price); fast and ultra-fast trade relevance for latency.
basicadvancedfastultra-fast
topicstringNogeneralSearch category. news returns recent articles with published dates.
generalnewsfinance
max_resultsintegerNo-Maximum number of results (0-20). Omit for Tavily's default.
chunks_per_sourceintegerNo-Maximum relevant content chunks per source (1-3, default 3). Applies to basic, advanced and fast.
time_rangestringNo-Only results published or updated within this window.
dayweekmonthyear
start_datestringNo-Only results published or updated after this date (YYYY-MM-DD).
end_datestringNo-Only results published or updated before this date (YYYY-MM-DD).
include_answerstringNo-Add an LLM-generated answer to the query. advanced is more detailed. Omit for no answer.
basicadvanced
include_raw_contentstringNo-Add the cleaned full page content of each result in this format. Omit for snippets only.
markdowntext
include_imagesbooleanNofalseAdd query-related images and per-result images.
include_image_descriptionsbooleanNofalseAdd a text description to each image (needs include_images).
include_faviconbooleanNofalseAdd each result's favicon URL.
include_published_datebooleanNofalseAdd published_date to each result (always on for topic=news).
include_domainsarrayNo-Only return results from these domains (e.g. ["core.today"]). Up to 300.
exclude_domainsarrayNo-Never return results from these domains. Up to 150.
countrystringNo-Boost results from a country, as a lowercase English name (e.g. south korea, united states). topic=general only.
languagestringNo-Boost results in a language - ISO 639-1 code or English name (e.g. ko, en).
auto_parametersbooleanNofalseLet Tavily pick parameters from the query intent (explicit values still win). May switch to advanced search - reserved at the advanced price and settled on the credits Tavily actually charged.
exact_matchbooleanNofalseOnly results containing the quoted phrases in the query.
safe_searchbooleanNofalseFilter adult or unsafe content. Not supported for fast or ultra-fast.

Common Parameters

Common parameters used when calling POST /v1/predictions.

ParameterTypeRequiredDefaultDescription
modelstringYes-Model identifier
inputobjectYes-Object containing the model-specific parameters from the table above
output_folderstringNo-Folder path for output files (max 256 chars, '..' not allowed)
webhook_urlstringNo-Webhook URL to call on completion
is_publicbooleanNofalseIf true, output files are also available via permanent public URLs

Examples

Search with an answer

Five results plus a short LLM-generated answer.

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "tavily/search",
  "input": {
    "query": "latest AI video generation models 2026",
    "search_depth": "basic",
    "max_results": 5,
    "include_answer": "basic"
  }
}'

Recent news from Korean sources

News from the past week, boosted toward Korea and Korean.

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "tavily/search",
  "input": {
    "query": "생성형 AI 규제",
    "topic": "news",
    "time_range": "week",
    "language": "ko",
    "max_results": 10
  }
}'

Deep search on chosen domains

advanced search limited to two domains, with full page content as markdown.

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "tavily/search",
  "input": {
    "query": "Seedance 2.5 reference to video pricing",
    "search_depth": "advanced",
    "include_domains": [
      "core.today",
      "byteplus.com"
    ],
    "include_raw_content": "markdown"
  }
}'

Tips & Best Practices

1The result is Tavily's JSON as-is: results[] (title, url, content, score), answer, images and usage.credits (the billed unit)
2Links in results are the original pages - they are not copied to your storage
3For full text of specific pages you already have, use tavily/extract instead of include_raw_content
4Write the query in the language you want results in; language and country only boost, they do not filter

Use Cases

Grounding chatbot and agent answers in current web information (RAG)
News monitoring and recent-event lookups
Research assistants that cite their sources