Maton

Exa

Access the Exa API with managed API key authentication. Perform neural web searches, retrieve page contents, find similar pages, get AI-generated answers with citations, and run async research tasks.

Reference

Perform a neural web search with optional content extraction.

POST /exa/search
Content-Type: application/json

{
  "query": "latest AI research papers",
  "numResults": 10
}

Request Parameters:

ParameterTypeRequiredDescription
querystringYesSearch query string
numResultsintegerNoNumber of results (max 100, default 10)
typestringNoSearch type: neural, auto (default), keyword
categorystringNoFilter by category: company, research paper, news, tweet, personal site, financial report, people
includeDomainsarrayNoOnly include these domains
excludeDomainsarrayNoExclude these domains
startPublishedDatestringNoISO 8601 date filter (after)
endPublishedDatestringNoISO 8601 date filter (before)
contentsobjectNoContent extraction options (see below)

Contents Options:

{
  "contents": {
    "text": true,
    "highlights": true,
    "summary": true
  }
}
OptionTypeDescription
textboolean/objectExtract full page text
highlightsboolean/objectExtract relevant snippets
summaryboolean/objectGenerate AI summary

Response:

{
  "requestId": "abc123",
  "resolvedSearchType": "neural",
  "results": [
    {
      "id": "https://example.com/article",
      "title": "Article Title",
      "url": "https://example.com/article",
      "publishedDate": "2024-01-15T00:00:00.000Z",
      "author": "Author Name",
      "text": "Full page content...",
      "highlights": ["Relevant snippet 1", "Relevant snippet 2"],
      "summary": "AI-generated summary..."
    }
  ],
  "costDollars": {
    "total": 0.005
  }
}

Get Contents

Retrieve full page contents for specific URLs.

POST /exa/contents
Content-Type: application/json

{
  "ids": ["https://example.com/page1", "https://example.com/page2"],
  "text": true
}

Request Parameters:

ParameterTypeRequiredDescription
idsarrayYesList of URLs to fetch content from
textbooleanNoInclude full page text
highlightsboolean/objectNoInclude relevant snippets
summaryboolean/objectNoGenerate AI summary

Response:

{
  "requestId": "abc123",
  "results": [
    {
      "id": "https://example.com/page1",
      "url": "https://example.com/page1",
      "title": "Page Title",
      "text": "Full page content..."
    }
  ]
}

Find Similar

Find pages similar to a given URL.

POST /exa/findSimilar
Content-Type: application/json

{
  "url": "https://example.com",
  "numResults": 10
}

Request Parameters:

ParameterTypeRequiredDescription
urlstringYesURL to find similar pages for
numResultsintegerNoNumber of results (max 100, default 10)
includeDomainsarrayNoOnly include these domains
excludeDomainsarrayNoExclude these domains
contentsobjectNoContent extraction options

Response:

{
  "requestId": "abc123",
  "results": [
    {
      "id": "https://similar-site.com",
      "title": "Similar Site",
      "url": "https://similar-site.com",
      "score": 0.95
    }
  ],
  "costDollars": {
    "total": 0.005
  }
}

Answer

Get an AI-generated answer to a question with citations.

POST /exa/answer
Content-Type: application/json

{
  "query": "What is machine learning?",
  "text": true
}

Request Parameters:

ParameterTypeRequiredDescription
querystringYesQuestion to answer
textbooleanNoInclude source text in response

Response:

{
  "requestId": "abc123",
  "answer": "Machine learning is a subset of artificial intelligence...",
  "citations": [
    {
      "id": "https://example.com/ml-guide",
      "url": "https://example.com/ml-guide",
      "title": "Machine Learning Guide"
    }
  ]
}

Create Research Task

POST /exa/research/v1
Content-Type: application/json

{
  "instructions": "What are the top AI companies and their main products?",
  "model": "exa-research"
}

Request Parameters:

ParameterTypeRequiredDescription
instructionsstringYesWhat to research (max 4096 chars)
modelstringNoModel to use: exa-research-fast, exa-research (default), exa-research-pro
outputSchemaobjectNoJSON Schema for structured output

Response:

{
  "researchId": "r_01abc123",
  "createdAt": 1772969504083,
  "model": "exa-research",
  "instructions": "What are the top AI companies...",
  "status": "running"
}

Get Research Task

GET /exa/research/v1/{researchId}

Query Parameters:

ParameterTypeDescription
eventsstringSet to true to include event log
streamstringSet to true for SSE streaming

Response (completed):

{
  "researchId": "r_01abc123",
  "status": "completed",
  "createdAt": 1772969504083,
  "finishedAt": 1772969520000,
  "model": "exa-research",
  "instructions": "What are the top AI companies...",
  "output": {
    "content": "Based on my research, the top AI companies are..."
  },
  "costDollars": {
    "total": 0.15,
    "numSearches": 5,
    "numPages": 20,
    "reasoningTokens": 1500
  }
}

Status values: pending, running, completed, canceled, failed

List Research Tasks

GET /exa/research/v1?limit=10

Query Parameters:

ParameterTypeDescription
limitintegerResults per page (1-50, default 10)
cursorstringPagination cursor

Response:

{
  "data": [
    {
      "researchId": "r_01abc123",
      "status": "completed",
      "model": "exa-research",
      "instructions": "What are the top AI companies..."
    }
  ],
  "hasMore": false,
  "nextCursor": null
}

Resources

On this page