Extract Data

Reference example

# Fixed reference example. Playground inputs do not update this sample.
curl --request POST \
  --url https://api.aisa.one/apis/v1/tavily/extract \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "urls": [
    "https://en.wikipedia.org/wiki/Artificial_intelligence"
  ]
}'

curl --request POST \
  --url https://api.aisa.one/apis/v1/tavily/extract \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "urls": [
    "https://en.wikipedia.org/wiki/Artificial_intelligence"
  ]
}
'

import requests

url = "https://api.aisa.one/apis/v1/tavily/extract"

payload = { "urls": ["https://en.wikipedia.org/wiki/Artificial_intelligence"] }
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({urls: ['https://en.wikipedia.org/wiki/Artificial_intelligence']})
};

fetch('https://api.aisa.one/apis/v1/tavily/extract', 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.aisa.one/apis/v1/tavily/extract",
  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' => [
        'https://en.wikipedia.org/wiki/Artificial_intelligence'
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($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.aisa.one/apis/v1/tavily/extract"

	payload := strings.NewReader("{\n  \"urls\": [\n    \"https://en.wikipedia.org/wiki/Artificial_intelligence\"\n  ]\n}")

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

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	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.aisa.one/apis/v1/tavily/extract")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"urls\": [\n    \"https://en.wikipedia.org/wiki/Artificial_intelligence\"\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.aisa.one/apis/v1/tavily/extract")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"urls\": [\n    \"https://en.wikipedia.org/wiki/Artificial_intelligence\"\n  ]\n}"

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

{
  "results": [
    {
      "url": "<string>",
      "title": "<string>",
      "raw_content": "<string>",
      "images": [
        "<string>"
      ],
      "favicon": "<string>"
    }
  ],
  "failed_results": [
    "<string>"
  ],
  "response_time": 123,
  "usage": {
    "credits": 123
  },
  "request_id": "<string>"
}

POST

https://api.aisa.one

apis

tavily

extract

Reference example

# Fixed reference example. Playground inputs do not update this sample.
curl --request POST \
  --url https://api.aisa.one/apis/v1/tavily/extract \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "urls": [
    "https://en.wikipedia.org/wiki/Artificial_intelligence"
  ]
}'

curl --request POST \
  --url https://api.aisa.one/apis/v1/tavily/extract \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "urls": [
    "https://en.wikipedia.org/wiki/Artificial_intelligence"
  ]
}
'

import requests

url = "https://api.aisa.one/apis/v1/tavily/extract"

payload = { "urls": ["https://en.wikipedia.org/wiki/Artificial_intelligence"] }
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({urls: ['https://en.wikipedia.org/wiki/Artificial_intelligence']})
};

fetch('https://api.aisa.one/apis/v1/tavily/extract', 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.aisa.one/apis/v1/tavily/extract",
  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' => [
        'https://en.wikipedia.org/wiki/Artificial_intelligence'
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($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.aisa.one/apis/v1/tavily/extract"

	payload := strings.NewReader("{\n  \"urls\": [\n    \"https://en.wikipedia.org/wiki/Artificial_intelligence\"\n  ]\n}")

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

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	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.aisa.one/apis/v1/tavily/extract")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"urls\": [\n    \"https://en.wikipedia.org/wiki/Artificial_intelligence\"\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.aisa.one/apis/v1/tavily/extract")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"urls\": [\n    \"https://en.wikipedia.org/wiki/Artificial_intelligence\"\n  ]\n}"

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

{
  "results": [
    {
      "url": "<string>",
      "title": "<string>",
      "raw_content": "<string>",
      "images": [
        "<string>"
      ],
      "favicon": "<string>"
    }
  ],
  "failed_results": [
    "<string>"
  ],
  "response_time": 123,
  "usage": {
    "credits": 123
  },
  "request_id": "<string>"
}

Fetch clean, parsed content for URLs you already have — from a search result, a sitemap, or a user. urls is required and takes several at once. Returns results[] with url, title, raw_content and images, plus a failed_results[] array — read that one, because a page that could not be fetched is reported there rather than raising an error. Choose format (markdown or text) and extract_depth. Measured at about 1 second for one page. Use this instead of post_tavily_search whenever you can already name the pages; searching for pages you can name costs more and may not return them. For a long list that can wait, post_firecrawl_batch_scrape runs it as a background job. To discover the URLs of a whole site first, use post_tavily_map.

First time? Point any MCP client at https://mcp.aisa.one/mcp — Claude Code, Codex, Cursor, VS Code and the rest. Authorization is OAuth: the client opens a browser, you click Allow once, and there is no key to paste. Your agent then reaches every endpoint through five tools: search, list_categories and get_details are free, use and batch_use are billed per call. Setup per client is in Connect via MCP; the live tool list and what each call costs are on aisa.one/mcp.

Set this endpoint up in your agent →

Cost and request rules

Published reference values are not an account-specific quote or a settled charge. For endpoints supporting X-AISA-Cost-Mode: quote, obtain a free quote for your exact request before execution; reconcile the settled cost with response metadata and Usage Logs. USD amounts use 1,000,000 integer micro-USD per dollar.

Default request reference estimate (USD): 0.024
Declared unit rate (USD): 0.008
Billing unit: tavily_credit
Cost contract: response_units
Published reference multiplier: 1.0
Settlement evidence source: response_body

Authorizations

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

urls

required

The URL or URLs to extract content from. A single URL string and an array of URL strings are both accepted.

Example:

[
  "https://en.wikipedia.org/wiki/Artificial_intelligence"
]

query

string

User intent for reranking extracted content chunks.

chunks_per_source

integer

default:3

Maximum number of relevant chunks returned per source. Available only when query is provided.

Required range: 1 <= x <= 5

extract_depth

enum<string>

default:basic

Depth of the extraction process.

Available options:

basic,

advanced

include_images

boolean

default:false

Include a list of images extracted from the URLs.

include_favicon

boolean

default:false

Include the favicon URL for each result.

format

enum<string>

default:markdown

Format of the extracted web page content.

Available options:

markdown,

text

timeout

number<float>

Maximum time in seconds to wait for URL extraction. If omitted, default timeouts depend on extract_depth: 10 seconds for basic and 30 seconds for advanced.

Required range: 1 <= x <= 60

include_usage

boolean

default:false

Include credit usage information in the response.

Response

Extraction results returned successfully.

results

object[]

Show child attributes

failed_results

string[]

List of URLs that could not be processed.

response_time

number<float>

Time in seconds it took to complete the request.

usage

object

Show child attributes

request_id

string

Unique request identifier.

Overview

Models

Search & Research

Finance & Crypto

Social & Media

SEO & Web Intel

Sales & Email

Travel & Other

Extract Data

Cost and request rules

Authorizations

Body

Response

​Cost and request rules

Authorizations

Body

Response

Cost and request rules