Tavily Research

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

Multi-search research assistant that explores a topic, analyzes sources, and produces a detailed research report with citations.

At a glance

FieldValue
Model idtavily-research
Input modalitiesText
Output modalitiesText
Context window-
Weight precision-
Featuresweb_search, citations, multi_search
Native inferenceNo
NewNo
Supported endpointsPOST /v1/research, POST /v1/search

Pricing

ChargeSpecRate
Miniaverage per task~$1.19
Proaverage per task~$2.75

Example request

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

Parameters

ParameterTypeRequiredDefaultDescription
querystringyes-The natural-language query to search/research/answer.
tavily_modelenumno"auto"auto = let Tavily pick. mini = cheaper. pro = deeper. · Allowed: mini, pro, auto
citation_formatenumno"numbered"How citations are formatted in the answer (inline | footnote | bibliography). · Allowed: numbered, mla, apa, chicago
include_answerbooleannotrueWhen true, Tavily returns a synthesized answer alongside the source list.
max_resultsnumberno5Cap on the number of source documents Tavily returns. · Range: 1 – 20
include_domainsarrayno-Array of domains to allow-list. Tavily restricts results to these domains when set.
exclude_domainsarrayno-Array of domains to block-list. Tavily skips any results from these domains.

Notes

Always uses advanced search depth. Returns synthesized answer plus citations.


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