Exa Contents

curl --request POST \
  --url https://api.novita.ai/v3/exa/contents \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "urls": [
    "<string>"
  ],
  "ids": [
    "<string>"
  ],
  "compliance": "<string>",
  "text": {
    "maxCharacters": 123,
    "includeHtmlTags": true,
    "verbosity": "<string>",
    "includeSections": [
      "<string>"
    ],
    "excludeSections": [
      "<string>"
    ]
  },
  "highlights": {
    "query": "<string>",
    "maxCharacters": 123
  },
  "summary": {
    "query": "<string>",
    "schema": {}
  },
  "extras": {
    "links": 123,
    "imageLinks": 123,
    "richImageLinks": 123,
    "richLinks": 123,
    "codeBlocks": 123
  },
  "livecrawlTimeout": 123,
  "maxAgeHours": 123,
  "subpages": 123,
  "subpageTarget": [
    "<string>"
  ]
}
'

import requests

url = "https://api.novita.ai/v3/exa/contents"

payload = {
    "urls": ["<string>"],
    "ids": ["<string>"],
    "compliance": "<string>",
    "text": {
        "maxCharacters": 123,
        "includeHtmlTags": True,
        "verbosity": "<string>",
        "includeSections": ["<string>"],
        "excludeSections": ["<string>"]
    },
    "highlights": {
        "query": "<string>",
        "maxCharacters": 123
    },
    "summary": {
        "query": "<string>",
        "schema": {}
    },
    "extras": {
        "links": 123,
        "imageLinks": 123,
        "richImageLinks": 123,
        "richLinks": 123,
        "codeBlocks": 123
    },
    "livecrawlTimeout": 123,
    "maxAgeHours": 123,
    "subpages": 123,
    "subpageTarget": ["<string>"]
}
headers = {
    "Content-Type": "<content-type>",
    "Authorization": "<authorization>"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': '<content-type>', Authorization: '<authorization>'},
  body: JSON.stringify({
    urls: ['<string>'],
    ids: ['<string>'],
    compliance: '<string>',
    text: {
      maxCharacters: 123,
      includeHtmlTags: true,
      verbosity: '<string>',
      includeSections: ['<string>'],
      excludeSections: ['<string>']
    },
    highlights: {query: '<string>', maxCharacters: 123},
    summary: {query: '<string>', schema: {}},
    extras: {
      links: 123,
      imageLinks: 123,
      richImageLinks: 123,
      richLinks: 123,
      codeBlocks: 123
    },
    livecrawlTimeout: 123,
    maxAgeHours: 123,
    subpages: 123,
    subpageTarget: ['<string>']
  })
};

fetch('https://api.novita.ai/v3/exa/contents', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.novita.ai/v3/exa/contents",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'urls' => [
        '<string>'
    ],
    'ids' => [
        '<string>'
    ],
    'compliance' => '<string>',
    'text' => [
        'maxCharacters' => 123,
        'includeHtmlTags' => true,
        'verbosity' => '<string>',
        'includeSections' => [
                '<string>'
        ],
        'excludeSections' => [
                '<string>'
        ]
    ],
    'highlights' => [
        'query' => '<string>',
        'maxCharacters' => 123
    ],
    'summary' => [
        'query' => '<string>',
        'schema' => [
                
        ]
    ],
    'extras' => [
        'links' => 123,
        'imageLinks' => 123,
        'richImageLinks' => 123,
        'richLinks' => 123,
        'codeBlocks' => 123
    ],
    'livecrawlTimeout' => 123,
    'maxAgeHours' => 123,
    'subpages' => 123,
    'subpageTarget' => [
        '<string>'
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: <authorization>",
    "Content-Type: <content-type>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.novita.ai/v3/exa/contents"

	payload := strings.NewReader("{\n  \"urls\": [\n    \"<string>\"\n  ],\n  \"ids\": [\n    \"<string>\"\n  ],\n  \"compliance\": \"<string>\",\n  \"text\": {\n    \"maxCharacters\": 123,\n    \"includeHtmlTags\": true,\n    \"verbosity\": \"<string>\",\n    \"includeSections\": [\n      \"<string>\"\n    ],\n    \"excludeSections\": [\n      \"<string>\"\n    ]\n  },\n  \"highlights\": {\n    \"query\": \"<string>\",\n    \"maxCharacters\": 123\n  },\n  \"summary\": {\n    \"query\": \"<string>\",\n    \"schema\": {}\n  },\n  \"extras\": {\n    \"links\": 123,\n    \"imageLinks\": 123,\n    \"richImageLinks\": 123,\n    \"richLinks\": 123,\n    \"codeBlocks\": 123\n  },\n  \"livecrawlTimeout\": 123,\n  \"maxAgeHours\": 123,\n  \"subpages\": 123,\n  \"subpageTarget\": [\n    \"<string>\"\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Content-Type", "<content-type>")
	req.Header.Add("Authorization", "<authorization>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.novita.ai/v3/exa/contents")
  .header("Content-Type", "<content-type>")
  .header("Authorization", "<authorization>")
  .body("{\n  \"urls\": [\n    \"<string>\"\n  ],\n  \"ids\": [\n    \"<string>\"\n  ],\n  \"compliance\": \"<string>\",\n  \"text\": {\n    \"maxCharacters\": 123,\n    \"includeHtmlTags\": true,\n    \"verbosity\": \"<string>\",\n    \"includeSections\": [\n      \"<string>\"\n    ],\n    \"excludeSections\": [\n      \"<string>\"\n    ]\n  },\n  \"highlights\": {\n    \"query\": \"<string>\",\n    \"maxCharacters\": 123\n  },\n  \"summary\": {\n    \"query\": \"<string>\",\n    \"schema\": {}\n  },\n  \"extras\": {\n    \"links\": 123,\n    \"imageLinks\": 123,\n    \"richImageLinks\": 123,\n    \"richLinks\": 123,\n    \"codeBlocks\": 123\n  },\n  \"livecrawlTimeout\": 123,\n  \"maxAgeHours\": 123,\n  \"subpages\": 123,\n  \"subpageTarget\": [\n    \"<string>\"\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.novita.ai/v3/exa/contents")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Content-Type"] = '<content-type>'
request["Authorization"] = '<authorization>'
request.body = "{\n  \"urls\": [\n    \"<string>\"\n  ],\n  \"ids\": [\n    \"<string>\"\n  ],\n  \"compliance\": \"<string>\",\n  \"text\": {\n    \"maxCharacters\": 123,\n    \"includeHtmlTags\": true,\n    \"verbosity\": \"<string>\",\n    \"includeSections\": [\n      \"<string>\"\n    ],\n    \"excludeSections\": [\n      \"<string>\"\n    ]\n  },\n  \"highlights\": {\n    \"query\": \"<string>\",\n    \"maxCharacters\": 123\n  },\n  \"summary\": {\n    \"query\": \"<string>\",\n    \"schema\": {}\n  },\n  \"extras\": {\n    \"links\": 123,\n    \"imageLinks\": 123,\n    \"richImageLinks\": 123,\n    \"richLinks\": 123,\n    \"codeBlocks\": 123\n  },\n  \"livecrawlTimeout\": 123,\n  \"maxAgeHours\": 123,\n  \"subpages\": 123,\n  \"subpageTarget\": [\n    \"<string>\"\n  ]\n}"

response = http.request(request)
puts response.read_body

{
  "requestId": "string",
  "results": [
    {
      "id": "string",
      "title": "string",
      "url": "string",
      "publishedDate": "string",
      "author": "string",
      "image": "string",
      "favicon": "string",
      "text": "string",
      "highlights": ["string"],
      "summary": "string",
      "subpages": [
        {
          "title": "string",
          "url": "string",
          "publishedDate": "string",
          "author": "string",
          "id": "string",
          "image": "string",
          "favicon": "string"
        }
      ],
      "extras": {
        "links": ["string"],
        "imageLinks": ["string"],
        "richImageLinks": [{}],
        "richLinks": [{}],
        "codeBlocks": [{"text": "string", "source": "string"}]
      },
      "entities": [
        {
          "id": "string",
          "type": "string",
          "version": 0,
          "properties": {}
        }
      ]
    }
  ],
  "statuses": [
    {
      "id": "string",
      "status": "string",
      "source": "string",
      "error": {
        "tag": "string",
        "httpStatusCode": 0
      }
    }
  ],
  "searchTime": 0
}

{
  "code": 400,
  "reason": "INVALID_REQUEST_BODY",
  "message": "Invalid request body | Validation error: must provide either ids or urls",
  "metadata": {
    "trace_id": "a4d532f86200dc7bb0df7fa6023860ca"
  }
}

{
  "code": 403,
  "reason": "INVALID_API_KEY",
  "message": "invalid api-key",
  "metadata": {}
}

{
  "code": 404,
  "reason": "PATH_NOT_FOUND",
  "message": "path not found for model",
  "metadata": {
    "trace_id": "3c3433f0cb475a04f9a4969b8c6ed903"
  }
}

{
  "code": 429,
  "reason": "RATE_LIMIT_EXCEEDED",
  "message": "rate limit exceeded, please retry later",
  "metadata": {
    "trace_id": "5f2a9c7e41b8d0a36e9f4c2b7d81a0e5"
  }
}

{
  "code": 500,
  "reason": "TASK_FAILED",
  "message": "upstream provider temporarily unavailable, please retry",
  "metadata": {
    "trace_id": "8846379c692d7218173460afe95640f1"
  }
}

{
  "code": 503,
  "reason": "SERVICE_UNAVAILABLE",
  "message": "service temporarily unavailable",
  "metadata": {
    "trace_id": "b7e3f1a9d24c05e8f63a1b9c7e05d2f4"
  }
}

POST

exa

contents

Exa Contents

curl --request POST \
  --url https://api.novita.ai/v3/exa/contents \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "urls": [
    "<string>"
  ],
  "ids": [
    "<string>"
  ],
  "compliance": "<string>",
  "text": {
    "maxCharacters": 123,
    "includeHtmlTags": true,
    "verbosity": "<string>",
    "includeSections": [
      "<string>"
    ],
    "excludeSections": [
      "<string>"
    ]
  },
  "highlights": {
    "query": "<string>",
    "maxCharacters": 123
  },
  "summary": {
    "query": "<string>",
    "schema": {}
  },
  "extras": {
    "links": 123,
    "imageLinks": 123,
    "richImageLinks": 123,
    "richLinks": 123,
    "codeBlocks": 123
  },
  "livecrawlTimeout": 123,
  "maxAgeHours": 123,
  "subpages": 123,
  "subpageTarget": [
    "<string>"
  ]
}
'

import requests

url = "https://api.novita.ai/v3/exa/contents"

payload = {
    "urls": ["<string>"],
    "ids": ["<string>"],
    "compliance": "<string>",
    "text": {
        "maxCharacters": 123,
        "includeHtmlTags": True,
        "verbosity": "<string>",
        "includeSections": ["<string>"],
        "excludeSections": ["<string>"]
    },
    "highlights": {
        "query": "<string>",
        "maxCharacters": 123
    },
    "summary": {
        "query": "<string>",
        "schema": {}
    },
    "extras": {
        "links": 123,
        "imageLinks": 123,
        "richImageLinks": 123,
        "richLinks": 123,
        "codeBlocks": 123
    },
    "livecrawlTimeout": 123,
    "maxAgeHours": 123,
    "subpages": 123,
    "subpageTarget": ["<string>"]
}
headers = {
    "Content-Type": "<content-type>",
    "Authorization": "<authorization>"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': '<content-type>', Authorization: '<authorization>'},
  body: JSON.stringify({
    urls: ['<string>'],
    ids: ['<string>'],
    compliance: '<string>',
    text: {
      maxCharacters: 123,
      includeHtmlTags: true,
      verbosity: '<string>',
      includeSections: ['<string>'],
      excludeSections: ['<string>']
    },
    highlights: {query: '<string>', maxCharacters: 123},
    summary: {query: '<string>', schema: {}},
    extras: {
      links: 123,
      imageLinks: 123,
      richImageLinks: 123,
      richLinks: 123,
      codeBlocks: 123
    },
    livecrawlTimeout: 123,
    maxAgeHours: 123,
    subpages: 123,
    subpageTarget: ['<string>']
  })
};

fetch('https://api.novita.ai/v3/exa/contents', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.novita.ai/v3/exa/contents",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'urls' => [
        '<string>'
    ],
    'ids' => [
        '<string>'
    ],
    'compliance' => '<string>',
    'text' => [
        'maxCharacters' => 123,
        'includeHtmlTags' => true,
        'verbosity' => '<string>',
        'includeSections' => [
                '<string>'
        ],
        'excludeSections' => [
                '<string>'
        ]
    ],
    'highlights' => [
        'query' => '<string>',
        'maxCharacters' => 123
    ],
    'summary' => [
        'query' => '<string>',
        'schema' => [
                
        ]
    ],
    'extras' => [
        'links' => 123,
        'imageLinks' => 123,
        'richImageLinks' => 123,
        'richLinks' => 123,
        'codeBlocks' => 123
    ],
    'livecrawlTimeout' => 123,
    'maxAgeHours' => 123,
    'subpages' => 123,
    'subpageTarget' => [
        '<string>'
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: <authorization>",
    "Content-Type: <content-type>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.novita.ai/v3/exa/contents"

	payload := strings.NewReader("{\n  \"urls\": [\n    \"<string>\"\n  ],\n  \"ids\": [\n    \"<string>\"\n  ],\n  \"compliance\": \"<string>\",\n  \"text\": {\n    \"maxCharacters\": 123,\n    \"includeHtmlTags\": true,\n    \"verbosity\": \"<string>\",\n    \"includeSections\": [\n      \"<string>\"\n    ],\n    \"excludeSections\": [\n      \"<string>\"\n    ]\n  },\n  \"highlights\": {\n    \"query\": \"<string>\",\n    \"maxCharacters\": 123\n  },\n  \"summary\": {\n    \"query\": \"<string>\",\n    \"schema\": {}\n  },\n  \"extras\": {\n    \"links\": 123,\n    \"imageLinks\": 123,\n    \"richImageLinks\": 123,\n    \"richLinks\": 123,\n    \"codeBlocks\": 123\n  },\n  \"livecrawlTimeout\": 123,\n  \"maxAgeHours\": 123,\n  \"subpages\": 123,\n  \"subpageTarget\": [\n    \"<string>\"\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Content-Type", "<content-type>")
	req.Header.Add("Authorization", "<authorization>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.novita.ai/v3/exa/contents")
  .header("Content-Type", "<content-type>")
  .header("Authorization", "<authorization>")
  .body("{\n  \"urls\": [\n    \"<string>\"\n  ],\n  \"ids\": [\n    \"<string>\"\n  ],\n  \"compliance\": \"<string>\",\n  \"text\": {\n    \"maxCharacters\": 123,\n    \"includeHtmlTags\": true,\n    \"verbosity\": \"<string>\",\n    \"includeSections\": [\n      \"<string>\"\n    ],\n    \"excludeSections\": [\n      \"<string>\"\n    ]\n  },\n  \"highlights\": {\n    \"query\": \"<string>\",\n    \"maxCharacters\": 123\n  },\n  \"summary\": {\n    \"query\": \"<string>\",\n    \"schema\": {}\n  },\n  \"extras\": {\n    \"links\": 123,\n    \"imageLinks\": 123,\n    \"richImageLinks\": 123,\n    \"richLinks\": 123,\n    \"codeBlocks\": 123\n  },\n  \"livecrawlTimeout\": 123,\n  \"maxAgeHours\": 123,\n  \"subpages\": 123,\n  \"subpageTarget\": [\n    \"<string>\"\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.novita.ai/v3/exa/contents")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Content-Type"] = '<content-type>'
request["Authorization"] = '<authorization>'
request.body = "{\n  \"urls\": [\n    \"<string>\"\n  ],\n  \"ids\": [\n    \"<string>\"\n  ],\n  \"compliance\": \"<string>\",\n  \"text\": {\n    \"maxCharacters\": 123,\n    \"includeHtmlTags\": true,\n    \"verbosity\": \"<string>\",\n    \"includeSections\": [\n      \"<string>\"\n    ],\n    \"excludeSections\": [\n      \"<string>\"\n    ]\n  },\n  \"highlights\": {\n    \"query\": \"<string>\",\n    \"maxCharacters\": 123\n  },\n  \"summary\": {\n    \"query\": \"<string>\",\n    \"schema\": {}\n  },\n  \"extras\": {\n    \"links\": 123,\n    \"imageLinks\": 123,\n    \"richImageLinks\": 123,\n    \"richLinks\": 123,\n    \"codeBlocks\": 123\n  },\n  \"livecrawlTimeout\": 123,\n  \"maxAgeHours\": 123,\n  \"subpages\": 123,\n  \"subpageTarget\": [\n    \"<string>\"\n  ]\n}"

response = http.request(request)
puts response.read_body

{
  "requestId": "string",
  "results": [
    {
      "id": "string",
      "title": "string",
      "url": "string",
      "publishedDate": "string",
      "author": "string",
      "image": "string",
      "favicon": "string",
      "text": "string",
      "highlights": ["string"],
      "summary": "string",
      "subpages": [
        {
          "title": "string",
          "url": "string",
          "publishedDate": "string",
          "author": "string",
          "id": "string",
          "image": "string",
          "favicon": "string"
        }
      ],
      "extras": {
        "links": ["string"],
        "imageLinks": ["string"],
        "richImageLinks": [{}],
        "richLinks": [{}],
        "codeBlocks": [{"text": "string", "source": "string"}]
      },
      "entities": [
        {
          "id": "string",
          "type": "string",
          "version": 0,
          "properties": {}
        }
      ]
    }
  ],
  "statuses": [
    {
      "id": "string",
      "status": "string",
      "source": "string",
      "error": {
        "tag": "string",
        "httpStatusCode": 0
      }
    }
  ],
  "searchTime": 0
}

{
  "code": 400,
  "reason": "INVALID_REQUEST_BODY",
  "message": "Invalid request body | Validation error: must provide either ids or urls",
  "metadata": {
    "trace_id": "a4d532f86200dc7bb0df7fa6023860ca"
  }
}

{
  "code": 403,
  "reason": "INVALID_API_KEY",
  "message": "invalid api-key",
  "metadata": {}
}

{
  "code": 404,
  "reason": "PATH_NOT_FOUND",
  "message": "path not found for model",
  "metadata": {
    "trace_id": "3c3433f0cb475a04f9a4969b8c6ed903"
  }
}

{
  "code": 429,
  "reason": "RATE_LIMIT_EXCEEDED",
  "message": "rate limit exceeded, please retry later",
  "metadata": {
    "trace_id": "5f2a9c7e41b8d0a36e9f4c2b7d81a0e5"
  }
}

{
  "code": 500,
  "reason": "TASK_FAILED",
  "message": "upstream provider temporarily unavailable, please retry",
  "metadata": {
    "trace_id": "8846379c692d7218173460afe95640f1"
  }
}

{
  "code": 503,
  "reason": "SERVICE_UNAVAILABLE",
  "message": "service temporarily unavailable",
  "metadata": {
    "trace_id": "b7e3f1a9d24c05e8f63a1b9c7e05d2f4"
  }
}

Retrieve page content, summaries, metadata, and fetch statuses for URLs or Exa document IDs. This is a passthrough to Exa’s Get Contents API, exposed through the Novita gateway with a platform route prefix. To authenticate with your Novita API key, get one from the Novita dashboard. Base URL: https://api.novita.ai.

Quickstart

curl -X POST 'https://api.novita.ai/v3/exa/contents' \
  -H 'Authorization: Bearer <api_key>' \
  -H 'Content-Type: application/json' \
  -d '{
    "urls": ["https://arxiv.org/abs/1706.03762"],
    "text": true
  }'

Running the quickstart above returns:

{
  "requestId": "0a6bd28991288444b8748646c5bd4bd9",
  "results": [
    {
      "id": "https://arxiv.org/abs/1706.03762",
      "title": "Attention Is All You Need",
      "url": "https://arxiv.org/abs/1706.03762",
      "publishedDate": "2025-08-23T00:00:00.000Z",
      "author": "Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, et al.",
      "text": "# Attention Is All You Need\n\n2025. Preprint. 6,569 citations.\n\n## Authors\n\n- Ashish Vaswani (Google (United States)): h-index 28; 10,049 citations…",
      "entities": [
        {
          "id": "https://exa.ai/library/publication/985dxcclwqj",
          "type": "publication",
          "version": 1,
          "properties": {
            "title": "Attention Is All You Need",
            "year": 2025,
            "date": "2025-08-23",
            "type": "preprint",
            "language": "en",
            "citationCount": 6569,
            "authors": [
              {"name": "Ashish Vaswani", "id": null}
            ]
          }
        }
      ]
    }
  ],
  "statuses": [
    {
      "id": "https://arxiv.org/abs/1706.03762",
      "status": "success",
      "source": "cached"
    }
  ],
  "searchTime": 8.12
}

Request Headers

All endpoints require platform API authentication.

string

required

Use application/json.

string

default:"Bearer YOUR_API_KEY"

required

Platform API key, formatted as Bearer YOUR_API_KEY.

Request Body

string[]

required

URLs to retrieve. This field is also backwards compatible with values previously supplied through ids. Range is 1 to 100 entries; each URL may be up to 2048 characters. Provide either urls or ids, but not both — supplying both returns a 400.

string[]

Exa document IDs to retrieve. Range is 1 to 100 entries; each ID may be up to 2048 characters. Provide either urls or ids, but not both — supplying both returns a 400.

string

Enterprise compliance mode. Only hipaa is supported.

boolean | object

Text extraction options. Default is false.

Show text properties

integer

Maximum number of text characters to return. Range is 1 to 10000.

boolean

Include lightweight HTML tags instead of plain text.

string

default:"compact"

Requested text verbosity. One of compact, standard, or full.

string[]

Semantic page sections to keep. Best-effort classification. Each entry is one of header, navigation, banner, body, sidebar, footer, or metadata.

string[]

Semantic page sections to drop. Best-effort classification. Each entry is one of header, navigation, banner, body, sidebar, footer, or metadata.

boolean | object

Highlight extraction options. Default is false.

Show highlights properties

string

Custom query used to select highlights.

integer

Maximum characters to return for highlights. Range is 1 to 10000.

boolean | object

Summary generation options. Pass true for a default summary, or an object to configure it.

Show summary properties

string

Custom instruction for summary generation.

object

Optional JSON schema for structured summary output.

object

Extra outputs to return from each page.

Show extras properties

integer

Number of links to return. Range is 0 to 1000.

integer

Number of image links to return. Range is 0 to 1000.

integer

Number of rich image links to return. Range is 0 to 1000.

integer

Number of rich links to return. Range is 0 to 1000.

integer

Number of code blocks to return. Range is 0 to 1000.

integer

Live crawl timeout in milliseconds. Range is greater than 0 and up to 90000; default is 10000.

integer

Maximum cache age in hours. Use 0 for fresh content and -1 to always use cache. Range is -1 to 720.

integer

Number of subpages to crawl. Range is 0 to 100; default is 0.

string | string[]

Term or terms used to find targeted subpages. String values are limited to 100 characters.

Examples

Extract text and highlights

curl -X POST 'https://api.novita.ai/v3/exa/contents' \
  -H 'Authorization: Bearer <api_key>' \
  -H 'Content-Type: application/json' \
  -d '{
    "urls": ["https://developer.mozilla.org/en-US/docs/Web/HTTP/Caching"],
    "text": {
      "maxCharacters": 4000
    },
    "highlights": {
      "query": "cache invalidation"
    }
  }'

Summarize a page

Use summary with a query to get a focused summary instead of raw text.

curl -X POST 'https://api.novita.ai/v3/exa/contents' \
  -H 'Authorization: Bearer <api_key>' \
  -H 'Content-Type: application/json' \
  -d '{
    "urls": ["https://en.wikipedia.org/wiki/CRISPR"],
    "summary": {
      "query": "What is this technology used for?"
    }
  }'

Include linked subpages

Use subpages with subpageTarget to also pull related pages the URL links to.

curl -X POST 'https://api.novita.ai/v3/exa/contents' \
  -H 'Authorization: Bearer <api_key>' \
  -H 'Content-Type: application/json' \
  -d '{
    "urls": ["https://docs.astro.build"],
    "text": true,
    "subpages": 3,
    "subpageTarget": "installation"
  }'

Force fresh content

Set maxAgeHours to 0 to bypass the cache and live-crawl the page.

curl -X POST 'https://api.novita.ai/v3/exa/contents' \
  -H 'Authorization: Bearer <api_key>' \
  -H 'Content-Type: application/json' \
  -d '{
    "urls": ["https://www.githubstatus.com"],
    "text": true,
    "maxAgeHours": 0
  }'

Response

string

Unique request identifier.

object[]

Content results.

Show result properties

string

Page title.

string

Page URL.

string

Published date when available.

string

Author when available.

string

Exa document ID.

string

Associated image URL.

string

Site favicon URL.

string

Extracted text when requested.

string[]

Highlight snippets when requested.

string

Generated summary when requested.

object[]

Subpage results when requested.

Show subpage properties

string

required

Subpage title.

string

required

Subpage URL.

string

Published date when available.

string

Author when available.

string

Exa document ID.

string

Associated image URL.

string

Site favicon URL.

object

Container for extra page data. Each child field is present only when its matching extras count is requested, and may be an empty array when the page has no such data.

Show extras properties

string[]

Extracted links when extras.links is requested.

string[]

Image links when extras.imageLinks is requested.

object[]

Rich image links when extras.richImageLinks is requested.

object[]

Rich links when extras.richLinks is requested.

object[]

Code blocks when extras.codeBlocks is requested.

Show codeBlock properties

string

Code block content.

string

Where the block was extracted from, such as text.

object[]

Structured entities extracted from the page. Each entity is a company, person, or publication. It may be absent or empty depending on the page.

Show entity properties

string

Stable entity identifier.

string

Entity discriminator. One of company, person, or publication.

integer

Entity schema version.

object

Type-specific fields. The shape depends on type.

Show company properties

string

Company name.

integer

Year the company was founded.

string

Short company description.

object

Workforce data.

Show workforce properties

number

Total headcount.

object

Headquarters location.

Show headquarters properties

string

Street address.

string

City.

string

Postal code.

string

Country.

object

Financial data.

Show financials properties

number

Annual revenue.

number

Total funding raised.

object

Most recent funding round.

Show fundingLatestRound properties

string

Round name, such as Series C.

string

Date of the round.

number

Amount raised in the round.

object

Web traffic data.

Show webTraffic properties

number

Monthly visits.

integer

Rank within the country.

number

Average visit duration in seconds.

object[]

Historical traffic data points.

Show history item properties

number

Traffic value for the period.

string

Period start, formatted as YYYY-MM.

string

Period end, formatted as YYYY-MM.

object

Research output.

Show research properties

integer

Number of published works.

integer

Total citations.

string[]

Research areas.

object[]

Notable works.

Show notableWork item properties

string

Work title.

integer

Publication year.

string

Publication venue.

integer

Number of citations.

string

Digital Object Identifier.

string

Work identifier.

string

Work type. One of article, book, book-chapter, dataset, dissertation, preprint, report, or review.

object[]

Leading researchers associated with the company.

Show topResearcher item properties

object

The researcher.

Show person properties

string

Researcher name.

string

Researcher identifier.

integer

Number of published works.

integer

Total citations.

Show person properties

string

Full name.

string

First name.

string

Last name.

string

Location.

object[]

Work history entries.

Show workHistory item properties

string

Job title.

string

Location.

object

Date range.

Show dates properties

string

Start date.

string

End date.

object

Employer.

Show company properties

string

Company identifier.

string

Company name.

object[]

Education entries.

Show educationHistory item properties

string

Degree earned.

object

Date range.

Show dates properties

string

Start date.

string

End date.

object

Institution.

Show institution properties

string

Institution identifier.

string

Institution name.

object

Research output.

Show research properties

integer

Number of published works.

integer

Total citations.

integer

h-index.

integer

Year of first publication.

integer

Year of most recent publication.

string[]

Research areas.

object[]

Notable works.

Show notableWork item properties

string

Work title.

integer

Publication year.

string

Publication venue.

integer

Number of citations.

string

Digital Object Identifier.

string

Work identifier.

string

Work type. One of article, book, book-chapter, dataset, dissertation, preprint, report, or review.

Show publication properties

string

Publication title.

integer

Publication year.

string

Publication date.

string

Publication type. One of article, book, book-chapter, dataset, dissertation, preprint, report, or review.

string

Language.

integer

Number of citations.

object[]

Authors.

Show author properties

string

Author name.

string

Author identifier.

integer

Number of references.

string

Abstract text.

object[]

Fetch status for each requested URL or document ID.

Show status properties

string

Requested URL or document ID.

string

Fetch status, such as success or error.

string

Content source, such as cached or crawled.

object

Error details when retrieval fails.

Show error properties

string

Machine-readable error tag, such as CRAWL_NOT_FOUND, CRAWL_TIMEOUT, or SOURCE_NOT_AVAILABLE.

integer

HTTP status code encountered while fetching the source, such as 404.

number

Time taken to serve the request, in milliseconds. Requests served from Exa’s cache (source: "cached") return in a few milliseconds, while pages that must be crawled live (source: "crawled") typically take on the order of one to several seconds.

Errors

Errors are returned as a JSON envelope with code, reason, message, and metadata. The platform validates and authenticates the request before forwarding it to Exa, so some errors originate at the platform and others are surfaced from upstream.

Status	`reason`	Meaning
`400`	`MISSING_API_KEY`	The `Authorization` header is absent.
`400`	`INVALID_REQUEST_BODY`	The body failed validation, such as omitting both `urls` and `ids`.
`403`	`INVALID_API_KEY`	The API key is invalid or not authorized.
`404`	`PATH_NOT_FOUND`	The route does not exist.
`429`	`RATE_LIMIT_EXCEEDED`	Too many requests. Slow down and retry with backoff.
`500`	`TASK_FAILED`	Internal or upstream provider failure. Transient failures are safe to retry.
`503`	`SERVICE_UNAVAILABLE`	The service is temporarily overloaded or down. Retry with backoff.

For validation failures, message is a JSON-encoded string carrying the detailed error and tag. The examples below show that inner detail decoded for readability.

{
  "requestId": "string",
  "results": [
    {
      "id": "string",
      "title": "string",
      "url": "string",
      "publishedDate": "string",
      "author": "string",
      "image": "string",
      "favicon": "string",
      "text": "string",
      "highlights": ["string"],
      "summary": "string",
      "subpages": [
        {
          "title": "string",
          "url": "string",
          "publishedDate": "string",
          "author": "string",
          "id": "string",
          "image": "string",
          "favicon": "string"
        }
      ],
      "extras": {
        "links": ["string"],
        "imageLinks": ["string"],
        "richImageLinks": [{}],
        "richLinks": [{}],
        "codeBlocks": [{"text": "string", "source": "string"}]
      },
      "entities": [
        {
          "id": "string",
          "type": "string",
          "version": 0,
          "properties": {}
        }
      ]
    }
  ],
  "statuses": [
    {
      "id": "string",
      "status": "string",
      "source": "string",
      "error": {
        "tag": "string",
        "httpStatusCode": 0
      }
    }
  ],
  "searchTime": 0
}

{
  "code": 400,
  "reason": "INVALID_REQUEST_BODY",
  "message": "Invalid request body | Validation error: must provide either ids or urls",
  "metadata": {
    "trace_id": "a4d532f86200dc7bb0df7fa6023860ca"
  }
}

{
  "code": 403,
  "reason": "INVALID_API_KEY",
  "message": "invalid api-key",
  "metadata": {}
}

{
  "code": 404,
  "reason": "PATH_NOT_FOUND",
  "message": "path not found for model",
  "metadata": {
    "trace_id": "3c3433f0cb475a04f9a4969b8c6ed903"
  }
}

{
  "code": 429,
  "reason": "RATE_LIMIT_EXCEEDED",
  "message": "rate limit exceeded, please retry later",
  "metadata": {
    "trace_id": "5f2a9c7e41b8d0a36e9f4c2b7d81a0e5"
  }
}

{
  "code": 500,
  "reason": "TASK_FAILED",
  "message": "upstream provider temporarily unavailable, please retry",
  "metadata": {
    "trace_id": "8846379c692d7218173460afe95640f1"
  }
}

{
  "code": 503,
  "reason": "SERVICE_UNAVAILABLE",
  "message": "service temporarily unavailable",
  "metadata": {
    "trace_id": "b7e3f1a9d24c05e8f63a1b9c7e05d2f4"
  }
}

Notes

All request bodies are JSON.
Extra Exa parameters not listed here may be passed through.
Response shapes can vary depending on request options.
This document intentionally omits billing-related fields.

References

For more details, see the Exa Contents API reference.

Last modified on July 30, 2026

Overview

Basic

Quota

Team Budget

API Key Model Access

Model APIs

GPUs

Exa Contents

Quickstart

Request Headers

Request Body

Examples

Extract text and highlights

Summarize a page

Include linked subpages

Force fresh content

Response

Errors

Notes

References

​Quickstart

​Request Headers

​Request Body

​Examples

​Extract text and highlights

​Summarize a page

​Include linked subpages

​Force fresh content

​Response

​Errors

​Notes

​References

Quickstart

Request Headers

Request Body

Examples

Extract text and highlights

Summarize a page

Include linked subpages

Force fresh content

Response

Errors

Notes

References