Search

POST

curl -X POST 'https://api.exa.ai/search' \
  -H 'Authorization: Bearer YOUR-EXA-API-KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "query": "Latest research in LLMs",
    "text": true
  }'

Get your Exa API key

Authorizations

Authorization

string

header

required

API key can be provided either via x-api-key header or Authorization header with Bearer scheme

Body

application/json

query

string

required

The query string for the search.

useAutoprompt

boolean

default:

true

Autoprompt converts your query to an Exa-style query. Enabled by default for auto search, optional for neural search, and not available for keyword search.

type

enum<string>

default:

auto

The type of search. Neural uses an embeddings-based model, keyword is google-like SERP. Default is auto, which automatically decides between keyword and neural.

Available options:

keyword,

neural,

auto

Response

200 - application/json

requestId

string

Unique identifier for the request

autopromptString

string

The prompt generated by autoprompt for your query

autoDate

string

Timestamp of when autoprompt was generated

resolvedSearchType

enum<string>

The search type that was actually used for this request

Available options:

neural,

keyword

results

object[]

A list of search results containing title, URL, published date, author, and score.

results.title

string

The title of the search result.

results.url

string

The URL of the search result.

results.publishedDate

string | null

An estimate of the creation date, from parsing HTML content. Format is YYYY-MM-DD.

results.author

string | null

If available, the author of the content.

results.score

number | null

A number from 0 to 1 representing similarity between the query/url and the result.

results.id

string

The temporary ID for the document. Useful for /contents endpoint.

results.image

string

The URL of an image associated with the search result, if available.

results.favicon

string

The URL of the favicon for the search result's domain.

results.text

string

The full content text of the search result.

results.highlights

string[]

Array of highlights extracted from the search result content.

results.highlightScores

number[]

Array of cosine similarity scores for each highlighted

results.summary

string

Summary of the webpage

results.subpages

object[]

Array of subpages for the search result.

results.subpages.title

string

The title of the search result.

results.subpages.url

string

The URL of the search result.

results.subpages.publishedDate

string | null

An estimate of the creation date, from parsing HTML content. Format is YYYY-MM-DD.

results.subpages.author

string | null

If available, the author of the content.

results.subpages.score

number | null

A number from 0 to 1 representing similarity between the query/url and the result.

results.subpages.id

string

The temporary ID for the document. Useful for /contents endpoint.

results.subpages.image

string

The URL of an image associated with the search result, if available.

results.subpages.favicon

string

The URL of the favicon for the search result's domain.

results.subpages.text

string

The full content text of the search result.

results.subpages.highlights

string[]

Array of highlights extracted from the search result content.

results.subpages.highlightScores

number[]

Array of cosine similarity scores for each highlighted

results.subpages.summary

string

Summary of the webpage

results.subpages.subpages

object[]

Array of subpages for the search result.

results.subpages.subpages.title

string

The title of the search result.

results.subpages.subpages.url

string

The URL of the search result.

results.subpages.subpages.publishedDate

string | null

An estimate of the creation date, from parsing HTML content. Format is YYYY-MM-DD.

results.subpages.subpages.author

string | null

If available, the author of the content.

results.subpages.subpages.score

number | null

A number from 0 to 1 representing similarity between the query/url and the result.

results.subpages.subpages.id

string

The temporary ID for the document. Useful for /contents endpoint.

results.subpages.subpages.image

string

The URL of an image associated with the search result, if available.

results.subpages.subpages.favicon

string

The URL of the favicon for the search result's domain.

results.subpages.subpages.text

string

The full content text of the search result.

results.subpages.subpages.highlights

string[]

Array of highlights extracted from the search result content.

results.subpages.subpages.highlightScores

number[]

Array of cosine similarity scores for each highlighted

results.subpages.subpages.summary

string

Summary of the webpage

results.subpages.subpages.subpages

object[]

Array of subpages for the search result.

results.subpages.subpages.extras

object

Results from extras.

results.subpages.extras

object

Results from extras.

results.extras

object

Results from extras.

searchType

enum<string>

For auto searches, indicates which search type was selected.

Available options:

neural,

keyword

costDollars

object

Quickstart Get contents

curl -X POST 'https://api.exa.ai/search' \
  -H 'Authorization: Bearer YOUR-EXA-API-KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "query": "Latest research in LLMs",
    "text": true
  }'

Getting Started

API Reference

RAG Quick Start Guide

Concepts

Admin

Get your Exa API key

Authorizations

Body

Response