Tavily Crawl

curl --request POST \
  --url https://api.novita.ai/v3/tavily/crawl \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "url": "<string>",
  "instructions": "<string>",
  "chunks_per_source": 123,
  "max_depth": 123,
  "max_breadth": 123,
  "limit": 123,
  "select_paths": [
    "<string>"
  ],
  "select_domains": [
    "<string>"
  ],
  "exclude_paths": [
    "<string>"
  ],
  "exclude_domains": [
    "<string>"
  ],
  "allow_external": true,
  "include_images": true,
  "extract_depth": "<string>",
  "format": "<string>",
  "include_favicon": true,
  "timeout": 123
}
'

import requests

url = "https://api.novita.ai/v3/tavily/crawl"

payload = {
    "url": "<string>",
    "instructions": "<string>",
    "chunks_per_source": 123,
    "max_depth": 123,
    "max_breadth": 123,
    "limit": 123,
    "select_paths": ["<string>"],
    "select_domains": ["<string>"],
    "exclude_paths": ["<string>"],
    "exclude_domains": ["<string>"],
    "allow_external": True,
    "include_images": True,
    "extract_depth": "<string>",
    "format": "<string>",
    "include_favicon": True,
    "timeout": 123
}
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({
    url: '<string>',
    instructions: '<string>',
    chunks_per_source: 123,
    max_depth: 123,
    max_breadth: 123,
    limit: 123,
    select_paths: ['<string>'],
    select_domains: ['<string>'],
    exclude_paths: ['<string>'],
    exclude_domains: ['<string>'],
    allow_external: true,
    include_images: true,
    extract_depth: '<string>',
    format: '<string>',
    include_favicon: true,
    timeout: 123
  })
};

fetch('https://api.novita.ai/v3/tavily/crawl', 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/tavily/crawl",
  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([
    'url' => '<string>',
    'instructions' => '<string>',
    'chunks_per_source' => 123,
    'max_depth' => 123,
    'max_breadth' => 123,
    'limit' => 123,
    'select_paths' => [
        '<string>'
    ],
    'select_domains' => [
        '<string>'
    ],
    'exclude_paths' => [
        '<string>'
    ],
    'exclude_domains' => [
        '<string>'
    ],
    'allow_external' => true,
    'include_images' => true,
    'extract_depth' => '<string>',
    'format' => '<string>',
    'include_favicon' => true,
    'timeout' => 123
  ]),
  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/tavily/crawl"

	payload := strings.NewReader("{\n  \"url\": \"<string>\",\n  \"instructions\": \"<string>\",\n  \"chunks_per_source\": 123,\n  \"max_depth\": 123,\n  \"max_breadth\": 123,\n  \"limit\": 123,\n  \"select_paths\": [\n    \"<string>\"\n  ],\n  \"select_domains\": [\n    \"<string>\"\n  ],\n  \"exclude_paths\": [\n    \"<string>\"\n  ],\n  \"exclude_domains\": [\n    \"<string>\"\n  ],\n  \"allow_external\": true,\n  \"include_images\": true,\n  \"extract_depth\": \"<string>\",\n  \"format\": \"<string>\",\n  \"include_favicon\": true,\n  \"timeout\": 123\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/tavily/crawl")
  .header("Content-Type", "<content-type>")
  .header("Authorization", "<authorization>")
  .body("{\n  \"url\": \"<string>\",\n  \"instructions\": \"<string>\",\n  \"chunks_per_source\": 123,\n  \"max_depth\": 123,\n  \"max_breadth\": 123,\n  \"limit\": 123,\n  \"select_paths\": [\n    \"<string>\"\n  ],\n  \"select_domains\": [\n    \"<string>\"\n  ],\n  \"exclude_paths\": [\n    \"<string>\"\n  ],\n  \"exclude_domains\": [\n    \"<string>\"\n  ],\n  \"allow_external\": true,\n  \"include_images\": true,\n  \"extract_depth\": \"<string>\",\n  \"format\": \"<string>\",\n  \"include_favicon\": true,\n  \"timeout\": 123\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.novita.ai/v3/tavily/crawl")

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  \"url\": \"<string>\",\n  \"instructions\": \"<string>\",\n  \"chunks_per_source\": 123,\n  \"max_depth\": 123,\n  \"max_breadth\": 123,\n  \"limit\": 123,\n  \"select_paths\": [\n    \"<string>\"\n  ],\n  \"select_domains\": [\n    \"<string>\"\n  ],\n  \"exclude_paths\": [\n    \"<string>\"\n  ],\n  \"exclude_domains\": [\n    \"<string>\"\n  ],\n  \"allow_external\": true,\n  \"include_images\": true,\n  \"extract_depth\": \"<string>\",\n  \"format\": \"<string>\",\n  \"include_favicon\": true,\n  \"timeout\": 123\n}"

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

{
  "400": {},
  "401": {},
  "403": {},
  "404": {},
  "429": {},
  "500": {},
  "502": {},
  "503": {},
  "base_url": "<string>",
  "results": [
    {}
  ],
  "response_time": 123,
  "request_id": "<string>",
  "url": "<string>",
  "raw_content": "<string>",
  "favicon": "<string>"
}

POST

tavily

crawl

Tavily Crawl

curl --request POST \
  --url https://api.novita.ai/v3/tavily/crawl \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "url": "<string>",
  "instructions": "<string>",
  "chunks_per_source": 123,
  "max_depth": 123,
  "max_breadth": 123,
  "limit": 123,
  "select_paths": [
    "<string>"
  ],
  "select_domains": [
    "<string>"
  ],
  "exclude_paths": [
    "<string>"
  ],
  "exclude_domains": [
    "<string>"
  ],
  "allow_external": true,
  "include_images": true,
  "extract_depth": "<string>",
  "format": "<string>",
  "include_favicon": true,
  "timeout": 123
}
'

import requests

url = "https://api.novita.ai/v3/tavily/crawl"

payload = {
    "url": "<string>",
    "instructions": "<string>",
    "chunks_per_source": 123,
    "max_depth": 123,
    "max_breadth": 123,
    "limit": 123,
    "select_paths": ["<string>"],
    "select_domains": ["<string>"],
    "exclude_paths": ["<string>"],
    "exclude_domains": ["<string>"],
    "allow_external": True,
    "include_images": True,
    "extract_depth": "<string>",
    "format": "<string>",
    "include_favicon": True,
    "timeout": 123
}
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({
    url: '<string>',
    instructions: '<string>',
    chunks_per_source: 123,
    max_depth: 123,
    max_breadth: 123,
    limit: 123,
    select_paths: ['<string>'],
    select_domains: ['<string>'],
    exclude_paths: ['<string>'],
    exclude_domains: ['<string>'],
    allow_external: true,
    include_images: true,
    extract_depth: '<string>',
    format: '<string>',
    include_favicon: true,
    timeout: 123
  })
};

fetch('https://api.novita.ai/v3/tavily/crawl', 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/tavily/crawl",
  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([
    'url' => '<string>',
    'instructions' => '<string>',
    'chunks_per_source' => 123,
    'max_depth' => 123,
    'max_breadth' => 123,
    'limit' => 123,
    'select_paths' => [
        '<string>'
    ],
    'select_domains' => [
        '<string>'
    ],
    'exclude_paths' => [
        '<string>'
    ],
    'exclude_domains' => [
        '<string>'
    ],
    'allow_external' => true,
    'include_images' => true,
    'extract_depth' => '<string>',
    'format' => '<string>',
    'include_favicon' => true,
    'timeout' => 123
  ]),
  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/tavily/crawl"

	payload := strings.NewReader("{\n  \"url\": \"<string>\",\n  \"instructions\": \"<string>\",\n  \"chunks_per_source\": 123,\n  \"max_depth\": 123,\n  \"max_breadth\": 123,\n  \"limit\": 123,\n  \"select_paths\": [\n    \"<string>\"\n  ],\n  \"select_domains\": [\n    \"<string>\"\n  ],\n  \"exclude_paths\": [\n    \"<string>\"\n  ],\n  \"exclude_domains\": [\n    \"<string>\"\n  ],\n  \"allow_external\": true,\n  \"include_images\": true,\n  \"extract_depth\": \"<string>\",\n  \"format\": \"<string>\",\n  \"include_favicon\": true,\n  \"timeout\": 123\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/tavily/crawl")
  .header("Content-Type", "<content-type>")
  .header("Authorization", "<authorization>")
  .body("{\n  \"url\": \"<string>\",\n  \"instructions\": \"<string>\",\n  \"chunks_per_source\": 123,\n  \"max_depth\": 123,\n  \"max_breadth\": 123,\n  \"limit\": 123,\n  \"select_paths\": [\n    \"<string>\"\n  ],\n  \"select_domains\": [\n    \"<string>\"\n  ],\n  \"exclude_paths\": [\n    \"<string>\"\n  ],\n  \"exclude_domains\": [\n    \"<string>\"\n  ],\n  \"allow_external\": true,\n  \"include_images\": true,\n  \"extract_depth\": \"<string>\",\n  \"format\": \"<string>\",\n  \"include_favicon\": true,\n  \"timeout\": 123\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.novita.ai/v3/tavily/crawl")

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  \"url\": \"<string>\",\n  \"instructions\": \"<string>\",\n  \"chunks_per_source\": 123,\n  \"max_depth\": 123,\n  \"max_breadth\": 123,\n  \"limit\": 123,\n  \"select_paths\": [\n    \"<string>\"\n  ],\n  \"select_domains\": [\n    \"<string>\"\n  ],\n  \"exclude_paths\": [\n    \"<string>\"\n  ],\n  \"exclude_domains\": [\n    \"<string>\"\n  ],\n  \"allow_external\": true,\n  \"include_images\": true,\n  \"extract_depth\": \"<string>\",\n  \"format\": \"<string>\",\n  \"include_favicon\": true,\n  \"timeout\": 123\n}"

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

{
  "400": {},
  "401": {},
  "403": {},
  "404": {},
  "429": {},
  "500": {},
  "502": {},
  "503": {},
  "base_url": "<string>",
  "results": [
    {}
  ],
  "response_time": 123,
  "request_id": "<string>",
  "url": "<string>",
  "raw_content": "<string>",
  "favicon": "<string>"
}

Tavily is a web data retrieval API designed for developers and AI applications. This document describes the Tavily passthrough endpoints exposed by the platform gateway. It is based on Tavily’s Crawl API with platform route prefixes applied. Base URL example: https://api.novita.ai Crawl a site starting from a root URL, following links to retrieve content from multiple pages.

Request Headers

All endpoints require platform API authentication.

string

required

Use application/json.

string

required

Platform API key, formatted as Bearer <api_key>.

Request Body

string

required

Crawl root URL.

string

Crawler instructions in natural language.

integer

Max number of content snippets per source to return. Default is 3; range is 1 to 5. Available only when instructions are set.

integer

Crawler depth limit. Default is 1; range is 1 to 5.

integer

Max links per page. Default is 20; range is 1 to 500.

integer

Link processing limit for crawler. Default is 50; minimum is 1.

string[]

Restrict URL paths matching these regex patterns.

string[]

Restrict domains matching these regex patterns.

string[]

Exclude URL paths matching these regex patterns.

string[]

Exclude domains matching these regex patterns.

boolean

Include external domain links.

boolean

Returns a list of images along with the response.

string

Extraction mode. Known values include basic and advanced. basic is set as the default value.

string

Output format of extracted content. Common values include markdown and text. markdown is set as the default value.

boolean

Include favicon URL from result.

float

Crawl operation time limit in seconds. Default is 150; range is 10 to 150.

Request Example

curl -s -X POST 'https://api.novita.ai/v3/tavily/crawl' \
  -H 'Authorization: Bearer sk-123' \
  -H 'Content-Type: application/json' \
  -d '{
    "url": "https://docs.tavily.com",
    "chunks_per_source": 3,
    "extract_depth": "basic",
    "format": "markdown",
    "max_depth": 1,
    "max_breadth": 5,
    "limit": 5,
    "allow_external": false,
    "include_images": false,
    "timeout": 120
  }'

Response

string

Crawl base URL.

object[]

Extracted content from crawled URLs. See Result Object.

float

Request duration in seconds.

string

Unique request identifier.

Result Object

string

Crawled URL.

string

Full page content.

string

Site favicon URL. Returned if include_favicon is true.

Errors

The platform may return standard HTTP errors before forwarding the request, and Tavily may return upstream errors after forwarding.

status

Invalid request body or unsupported parameter value.

status

Missing or invalid API key.

status

Access denied by platform or upstream provider, or the URL is not supported.

status

Route or requested resource not found.

status

Rate limit exceeded.

status

Internal server error.

status

Upstream provider error.

status

Service unavailable.

Notes

All request bodies are JSON.
Extra Tavily 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 Tavily Crawl API reference.

Last modified on June 23, 2026

Overview

Basic

Quota

Team Budget

API Key Model Access

Model APIs

GPUs

Tavily Crawl

Request Headers

Request Body

Request Example

Response

Result Object

Errors

Notes

References

​Request Headers

​Request Body

​Request Example

​Response

​Result Object

​Errors

​Notes

​References

Request Headers

Request Body

Request Example

Response

Result Object

Errors

Notes

References