Exa · Search

Exa / Neural web search

Neural or keyword web search. Send query; type (auto, fast, deep and others), numResults, category, domains and dates refine it, and contents adds page text. Returns ranked results with title, URL, date and highlights. The charge follows Exa's reported costDollars.

Private Gateway connection

Data below comes from the configured private Gateway. Provider activation remains governed by its evidence and policy gates.

unverifiedRequest shape unavailableUnverified

Published API evidence

Public metadata only. Response bodies, credentials, and internal review notes are never displayed.

No verification date is claimed. No response capture is claimed.

Request parameters

additionalQueries body · optional
Additional query variations, deep-search types only.
category body · optional
Data category hint. company/people categories reject startPublishedDate/endPublishedDate/excludeDomains with a 400.
contents body · optional
Content options for the returned results -- each requested type (highlights/text/summary) adds $0.001/page.
endPublishedDate body · optional
Only links published before this ISO 8601 date.
excludeDomains body · optional
Never these hostnames/domain paths. Rejected with a 400 alongside category company/people.
includeDomains body · optional
Only these hostnames/domain paths (e.g. example.com, example.com/docs, *.example.com).
numResults body · optional
Results to return. The cost dial above 10 -- each additional result is $0.001.
outputSchema body · optional
JSON schema for synthesized output (root type "text" or "object"). Adds ~2s synthesis latency. Depth 2, max 10 top-level properties.
query body · required
The query string for the search. Example: "Latest developments in LLM capabilities"
startPublishedDate body · optional
Only links published after this ISO 8601 date.
systemPrompt body · optional
Additional instructions guiding generated output/agent behavior (source preferences, novelty/duplication constraints).
type body · optional
auto (default) balances quality/speed; fast reduces latency; instant optimizes for minimum response time; deep-lite/deep/deep-reasoning trade latency for research depth (~1s/450ms/250ms/4-15s/12-40s respectively).

Provider docs How to run it