⭐ Getting Started:

Python:

pip install tavily-python

from tavily import TavilyClient

tavily_client = TavilyClient(api_key="tvly-YOUR_API_KEY")
response = tavily_client.search("Who is Leo Messi?")

print(response)

JavaScript / TypeScript:

npm install @tavily/core

const { tavily } = require("@tavily/core");

const tvly = tavily({ apiKey: "tvly-YOUR_API_KEY" });
const response = await tvly.search("Who is Leo Messi?");

console.log(response);

For full API reference & guides: docs .

---

What is Tavily?

The web access layer for AI applications. Tavily provides fast, reliable APIs that let developers easily:

🔍 Search the web

Optimized for relevancy and low latency. Get real-time, contextual information from across the web with intelligent content extraction and ranking that prioritizes the most relevant results for your AI applications.

📄 Extract structured data from URLs

Supporting summaries, Markdown, or cleaned text. Transform any webpage into LLM-ready data with automatic content cleaning, format conversion, and text extraction that preserves structure and meaning.

🕸️ Crawl entire domains at scale

Optimized for intelligent URL decisions and results. Navigate complex websites with smart crawling strategies that respect robots.txt, handle dynamic content, and efficiently discover all accessible pages.

Built specifically for AI agents and RAG workflows.