Start Crawl Process

Reference example

# Fixed reference example. Playground inputs do not update this sample.
curl --request POST \
  --url https://api.aisa.one/apis/v1/tavily/crawl \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "url": "docs.tavily.com"
}'

curl --request POST \
  --url https://api.aisa.one/apis/v1/tavily/crawl \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "url": "docs.tavily.com"
}
'

import requests

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

payload = { "url": "docs.tavily.com" }
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({url: 'docs.tavily.com'})
};

fetch('https://api.aisa.one/apis/v1/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.aisa.one/apis/v1/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' => 'docs.tavily.com'
  ]),
  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/crawl"

	payload := strings.NewReader("{\n  \"url\": \"docs.tavily.com\"\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/crawl")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"url\": \"docs.tavily.com\"\n}")
  .asString();

require 'uri'
require 'net/http'

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

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  \"url\": \"docs.tavily.com\"\n}"

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

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

POST

https://api.aisa.one

apis

tavily

crawl

Reference example

# Fixed reference example. Playground inputs do not update this sample.
curl --request POST \
  --url https://api.aisa.one/apis/v1/tavily/crawl \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "url": "docs.tavily.com"
}'

curl --request POST \
  --url https://api.aisa.one/apis/v1/tavily/crawl \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "url": "docs.tavily.com"
}
'

import requests

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

payload = { "url": "docs.tavily.com" }
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({url: 'docs.tavily.com'})
};

fetch('https://api.aisa.one/apis/v1/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.aisa.one/apis/v1/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' => 'docs.tavily.com'
  ]),
  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/crawl"

	payload := strings.NewReader("{\n  \"url\": \"docs.tavily.com\"\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/crawl")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"url\": \"docs.tavily.com\"\n}")
  .asString();

require 'uri'
require 'net/http'

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

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  \"url\": \"docs.tavily.com\"\n}"

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

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

从根 url 遍历站点并返回沿途页面的正文。可用自然语言 instructions 加正则路径/域名过滤引导，并用 max_depth、max_breadth、limit 限定范围。返回 base_url 和 results[]，每条含 url 与 raw_content。实测限制 3 个页面时约 4.5 秒；成本和耗时随你设的上限增长，所以务必设。适合需要覆盖某一个站点的场景 —— 文档站、商品目录、竞品博客。它是同步返回的，而 post_firecrawl_crawl 不是：那个作为后台任务跑，适合大到等不起的爬取。若只是几个已知页面，post_tavily_extract 便宜得多；想在付费爬取前先看看站有多大，先跑 post_tavily_map。

第一次用？ 把任意 MCP 客户端指向 https://mcp.aisa.one/mcp —— Claude Code、 Codex、Cursor、VS Code 都可以。鉴权走 OAuth：客户端打开浏览器，你点一次 Allow，不需要粘贴任何 key。之后智能体通过几个元工具调用所有端点： search、list_categories、get_details 和 batch_quote 免费，batch_use 按次计费。各客户端的接入步骤见通过 MCP 连接；实时工具列表和每次调用的价格见 aisa.one/zh-cn/mcp。

在你的 agent 里把这个端点跑起来 →

请求规范

方法与路径: POST /apis/v1/tavily/crawl
可用状态: enabled
请求 URL 模板: https://api.aisa.one/apis/v1/tavily/crawl
Runtime 事实版本: ea2301436db90d0b30e55885326cd5057bea93ff7d26d9bced8e1ae7f1911ef4

完整 OpenAPI 定义有效请求与价格声明（包括认证和引用的 schema）：

{
  "operationId": "post_tavily_crawl",
  "method": "POST",
  "path": "/apis/v1/tavily/crawl",
  "servers": [
    {
      "url": "https://api.aisa.one"
    }
  ],
  "parameters": [],
  "security": [
    {
      "bearerAuth": []
    }
  ],
  "requestBody": {
    "content": {
      "application/json": {
        "schema": {
          "properties": {
            "allow_external": {
              "default": true,
              "description": "Include external domain links in the final results list.",
              "type": "boolean"
            },
            "chunks_per_source": {
              "default": 3,
              "description": "Maximum number of relevant chunks returned per source.",
              "maximum": 5,
              "minimum": 1,
              "type": "integer"
            },
            "exclude_domains": {
              "description": "Regex patterns to exclude specific domains or subdomains from crawling.",
              "items": {
                "type": "string"
              },
              "type": "array"
            },
            "exclude_paths": {
              "description": "Regex patterns to exclude URLs with specific path patterns.",
              "items": {
                "type": "string"
              },
              "type": "array"
            },
            "extract_depth": {
              "default": "basic",
              "description": "Depth of the extraction process.",
              "enum": [
                "basic",
                "advanced"
              ],
              "type": "string"
            },
            "format": {
              "default": "markdown",
              "description": "Format of the extracted web page content.",
              "enum": [
                "markdown",
                "text"
              ],
              "type": "string"
            },
            "include_favicon": {
              "default": false,
              "description": "Include the favicon URL for each result.",
              "type": "boolean"
            },
            "include_images": {
              "default": false,
              "description": "Include images in the crawl results.",
              "type": "boolean"
            },
            "include_usage": {
              "default": false,
              "description": "Include credit usage information in the response.",
              "type": "boolean"
            },
            "instructions": {
              "description": "Natural language instructions for the crawler.",
              "type": "string"
            },
            "limit": {
              "default": 50,
              "description": "Total number of links the crawler will process before stopping.",
              "minimum": 1,
              "type": "integer"
            },
            "max_breadth": {
              "default": 20,
              "description": "Max number of links to follow per level of the tree.",
              "maximum": 500,
              "minimum": 1,
              "type": "integer"
            },
            "max_depth": {
              "default": 1,
              "description": "Max depth of the crawl.",
              "maximum": 5,
              "minimum": 1,
              "type": "integer"
            },
            "select_domains": {
              "description": "Regex patterns to select crawling to specific domains or subdomains.",
              "items": {
                "type": "string"
              },
              "type": "array"
            },
            "select_paths": {
              "description": "Regex patterns to select only URLs with specific path patterns.",
              "items": {
                "type": "string"
              },
              "type": "array"
            },
            "timeout": {
              "default": 150,
              "description": "Maximum time in seconds to wait for the crawl operation.",
              "format": "float",
              "maximum": 150,
              "minimum": 10,
              "type": "number"
            },
            "url": {
              "description": "The root URL to begin the crawl.",
              "example": "docs.tavily.com",
              "type": "string"
            }
          },
          "required": [
            "url"
          ],
          "type": "object"
        }
      }
    },
    "required": true
  },
  "x-aisa-status": "enabled",
  "x-aisa-pricing": {
    "cost_contract": "response_units",
    "customer_multiplier": 1.0,
    "customer_pricing": "provider_cost_multiplier",
    "default_request_estimate_usd": 0.024,
    "estimate_source": "profile_seed",
    "evidence_source": "response_body",
    "unit": "tavily_credit",
    "unit_rate_usd": 0.008
  },
  "components": {
    "securitySchemes": {
      "bearerAuth": {
        "scheme": "bearer",
        "type": "http"
      }
    }
  }
}

费用与请求规则

按用量计费；默认请求预估费用：$0.024 USD（不是固定价格）。声明的单位费率：每 tavily_credit $0.008 USD。最终费用以账户适用价格及实际结算为准。公开参考值不是你的账户报价或最终扣费。对于支持 X-AISA-Cost-Mode: quote 的接口，执行前请针对完整请求获取免费报价；执行后通过响应费用元数据和 Usage Logs 核对结算费用。1 USD 等于 1,000,000 个整数 micro-USD。

默认请求参考估价（USD）: 0.024
声明的单位费率（USD）: 0.008
计费单位: tavily_credit
计费依据: response_units
公开参考倍率: 1.0
结算证据来源: response_body

授权

Authorization

string

header

必填

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

请求体

application/json

url

string

必填

开始抓取的根 URL。

示例:

"docs.tavily.com"

allow_external

boolean

默认值:true

在最终结果列表中包含外部域名链接。

chunks_per_source

integer

默认值:3

每个来源返回的相关文本块的最大数量。

必填范围: 1 <= x <= 5

exclude_domains

string[]

用于从抓取中排除特定域名或子域名的正则表达式模式。

exclude_paths

string[]

用于排除具有特定路径模式的 URL 的正则表达式模式。

extract_depth

enum<string>

默认值:basic

提取过程的深度。

可用选项:

basic,

advanced

format

enum<string>

默认值:markdown

提取的网页内容格式。

可用选项:

markdown,

text

include_favicon

boolean

默认值:false

为每个结果包含 favicon URL。

include_images

boolean

默认值:false

在抓取结果中包含图片。

include_usage

boolean

默认值:false

在响应中包含信用额度用量信息。

instructions

string

用于爬虫的自然语言指令。

limit

integer

默认值:50

爬虫停止前将处理的链接总数。

必填范围: x >= 1

max_breadth

integer

默认值:20

树中每一层可跟踪的最大链接数量。

必填范围: 1 <= x <= 500

max_depth

integer

默认值:1

最大抓取深度。

必填范围: 1 <= x <= 5

select_domains

string[]

用于选择仅抓取特定域名或子域名的正则表达式模式。

select_paths

string[]

用于仅选择具有特定路径模式的 URL 的正则表达式模式。

timeout

number<float>

默认值:150

等待抓取操作完成的最长时间（秒）。

必填范围: 10 <= x <= 150

响应

已成功返回抓取结果。

base_url

string

已抓取的基础 URL。

request_id

string

唯一请求标识符。

response_time

number<float>

完成请求所用的时间（秒）。

results

object[]

Show child attributes

usage

object

Show child attributes

概览

模型

搜索与研究

金融与加密

社交与媒体

SEO 与网站情报

销售与邮件

出行与其他

Start Crawl Process

请求规范

费用与请求规则

授权

请求体

响应

​请求规范

​费用与请求规则

授权

请求体

响应

请求规范

费用与请求规则