tavily-api（tavily API 搜索）

Tavily

Access the Tavily API with managed API key authentication. Perform AI-powered web searches, extract content from URLs, crawl websites, map site structure, and run in-depth research tasks.

Quick Start

# Search the web
python <<'EOF'
import urllib.request, os, json
data = json.dumps({"query": "latest AI news", "max_results": 5}).encode()
req = urllib.request.Request('https://gateway.maton.ai/tavily/search', data=data, method='POST')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
req.add_header('Content-Type', 'application/json')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Base URL

https://gateway.maton.ai/tavily/{endpoint}

Replace {endpoint} with the Tavily API endpoint (search, extract, crawl, map, research). The gateway proxies requests to api.tavily.com and automatically injects your API key.

Authentication

All requests require the Maton API key in the Authorization header:

Authorization: Bearer $MATON_API_KEY

Environment Variable: Set your API key as MATON_API_KEY:

export MATON_API_KEY="YOUR_API_KEY"

Getting Your API Key

1. Sign in or create an account at maton.ai
2. Go to maton.ai/settings
3. Copy your API key

Connection Management

Manage your Tavily API key connections at https://ctrl.maton.ai.

List Connections

python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://ctrl.maton.ai/connections?app=tavily&status=ACTIVE')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Create Connection

python <<'EOF'
import urllib.request, os, json
data = json.dumps({'app': 'tavily', 'method': 'API_KEY'}).encode()
req = urllib.request.Request('https://ctrl.maton.ai/connections', data=data, method='POST')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
req.add_header('Content-Type', 'application/json')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Open the returned url in a browser to enter your Tavily API key.

Get Connection

python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://ctrl.maton.ai/connections/{connection_id}')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Delete Connection

python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://ctrl.maton.ai/connections/{connection_id}', method='DELETE')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Specifying Connection

If you have multiple Tavily connections, specify which one to use with the Maton-Connection header:

python <<'EOF'
import urllib.request, os, json
data = json.dumps({"query": "AI news"}).encode()
req = urllib.request.Request('https://gateway.maton.ai/tavily/search', data=data, method='POST')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
req.add_header('Content-Type', 'application/json')
req.add_header('Maton-Connection', '{connection_id}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

If omitted, the gateway uses the default (oldest) active connection.

API Reference

Search

Perform AI-powered web search with optional answer generation.

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

{
  "query": "What is artificial intelligence?",
  "max_results": 5
}

Request Parameters:

Response:

{
  "query": "What is artificial intelligence?",
  "answer": "Artificial intelligence (AI) is...",
  "results": [
    {
      "title": "What is AI?",
      "url": "https://example.com/ai",
      "content": "AI is a branch of computer science...",
      "score": 0.95
    }
  ],
  "response_time": 0.55
}

Extract

Extract content from one or more URLs.

POST /tavily/extract
Content-Type: application/json

{
  "urls": ["https://example.com/article"],
  "format": "markdown"
}

Request Parameters:

Response:

{
  "results": [
    {
      "url": "https://example.com/article",
      "raw_content": "# Article Title\
\
Content in markdown...",
      "images": [],
      "favicon": "https://example.com/favicon.ico"
    }
  ],
  "failed_results": [],
  "response_time": 0.01
}

Map

Discover URLs from a website without extracting content.

POST /tavily/map
Content-Type: application/json

{
  "url": "https://example.com",
  "limit": 20
}

Request Parameters:

Response:

{
  "base_url": "https://example.com",
  "results": [
    "https://example.com/about",
    "https://example.com/products",
    "https://example.com/contact"
  ],
  "response_time": 0.1
}

Crawl

Crawl a website and extract content from discovered pages.

POST /tavily/crawl
Content-Type: application/json

{
  "url": "https://example.com",
  "limit": 10,
  "max_depth": 2
}

Request Parameters:

Response:

{
  "base_url": "https://example.com",
  "results": [
    {
      "url": "https://example.com/about",
      "raw_content": "# About Us\
\
Content...",
      "favicon": "https://example.com/favicon.ico"
    }
  ],
  "response_time": 0.09
}

Research Tasks

Run async research tasks that gather sources and synthesize findings.

Create Research Task

POST /tavily/research
Content-Type: application/json

{
  "input": "What are the latest developments in AI safety?",
  "model": "mini"
}

Request Parameters:

Response:

{
  "request_id": "582a6eec-9a10-43ba-830f-d9a1aeb19f07",
  "status": "pending",
  "input": "What are the latest developments in AI safety?",
  "model": "mini",
  "created_at": "2026-03-08T11:36:12.674507+00:00",
  "response_time": 0.05
}

Get Research Task

GET /tavily/research/{request_id}

Response (completed):

{
  "request_id": "582a6eec-9a10-43ba-830f-d9a1aeb19f07",
  "status": "completed",
  "content": "## AI Safety Developments\
\
Research findings...",
  "sources": [
    {
      "title": "Source Title",
      "url": "https://example.com/source",
      "favicon": "https://example.com/favicon.ico"
    }
  ],
  "created_at": "2026-03-08T11:36:12.674507+00:00",
  "response_time": 45
}

Status values: pending, in_progress, completed, failed

Code Examples

JavaScript

// Search with answer
const response = await fetch('https://gateway.maton.ai/tavily/search', {
  method: 'POST',
  headers: {
    'Authorization': `Bearer ${process.env.MATON_API_KEY}`,
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    query: 'latest AI news',
    max_results: 5,
    include_answer: true
  })
});
const data = await response.json();

Python

import os
import requests

# Search with answer
response = requests.post(
    'https://gateway.maton.ai/tavily/search',
    headers={'Authorization': f'Bearer {os.environ["MATON_API_KEY"]}'},
    json={
        'query': 'latest AI news',
        'max_results': 5,
        'include_answer': True
    }
)
data = response.json()

Notes

• Search endpoints return AI-generated answers when include_answer is enabled
• Map returns URLs only; Crawl returns URLs with extracted content
• Using instructions parameter in crawl/map doubles the credit cost
• Research tasks are async - poll with GET to check status
• Research models: mini (fast/efficient), pro (comprehensive)
• IMPORTANT: When piping curl output to jq or other commands, environment variables like $MATON_API_KEY may not expand correctly in some shell environments

Error Handling

Resources

• Tavily API Documentation
• Search API Reference
• Extract API Reference
• Crawl API Reference
• Research API Reference
• Tavily Dashboard
• Maton Community
• Maton Support