# Tavily Search — Search API Built for AI Agents

> Tavily Search returns LLM-ready answers from the web — not link lists. One call gets snippets, citations, optional generated answer. Free tier 1K/mo.

## Install

Copy the content below into your project:

## Quick Use

1. Sign up at tavily.com → copy API key
2. `pip install tavily-python` (or `npm install @tavily/core`)
3. `client.search(query=..., include_answer=True)` returns LLM-ready snippets

---

## Intro

Tavily Search is the search API designed for AI agents and RAG. Unlike Google Custom Search or Bing API, Tavily returns curated content snippets ready to feed an LLM — not a list of URLs to scrape. Optional `include_answer` gives a generated synthesis. Best for: AI agents that need fresh facts, citations, real-time info. Works with: Tavily REST API, Python / TypeScript SDK, MCP server. Setup time: 2 minutes.

---

### Hello world

```python
from tavily import TavilyClient

client = TavilyClient(api_key=os.environ["TAVILY_API_KEY"])

response = client.search(
    query="What is the latest version of Python?",
    search_depth="advanced",
    include_answer=True,
    include_raw_content=False,
    max_results=5,
)

print(response["answer"])
# "As of October 2024, the latest stable version of Python is 3.13.0..."

for r in response["results"]:
    print(f"{r['title']} — {r['url']}")
    print(r["content"][:200])
```

### Search depth

| Mode | Use | Cost |
|---|---|---|
| `basic` | Quick fact lookups | 1 credit |
| `advanced` | Multi-source research, RAG | 2 credits |

Advanced mode crawls more sources and runs a rerank pass — better for answer quality, slightly higher latency and cost.

### Filter by domain

```python
# Whitelist
response = client.search(
    query="Latest LangChain release notes",
    include_domains=["python.langchain.com", "github.com"],
)

# Blacklist
response = client.search(
    query="Best vector databases",
    exclude_domains=["medium.com"],  # avoid SEO blogspam
)
```

### As MCP

```json
{
  "mcpServers": {
    "tavily": {
      "command": "npx",
      "args": ["-y", "tavily-mcp"],
      "env": { "TAVILY_API_KEY": "tvly-..." }
    }
  }
}
```

Now Claude Code / Cursor can call `tavily_search`, `tavily_extract`, `tavily_crawl` directly.

---

### FAQ

**Q: Is Tavily free?**
A: Yes — free tier 1,000 API credits/month, no credit card needed. Paid plans add higher quotas and team features. Pricing on tavily.com.

**Q: How is Tavily different from Google search via SerpAPI?**
A: SerpAPI returns Google's HTML organic results — you scrape and clean. Tavily already runs the cleaning, ranking, and (optionally) synthesis. Tavily is purpose-built for LLM consumption; SerpAPI is purpose-built for SERP scraping.

**Q: Can I use Tavily with LangChain?**
A: Yes — `langchain_community.tools.tavily_search.TavilySearchResults` is a built-in LangChain tool. Same for LlamaIndex, CrewAI, Pydantic AI.

---

## Source & Thanks

> Built by [Tavily](https://github.com/tavily-ai). Commercial product with free tier.
>
> [tavily-ai/tavily-python](https://github.com/tavily-ai/tavily-python) — ⭐ Active

---

<!-- ZH -->

## 快速使用

1. 在 tavily.com 注册，复制 API key
2. `pip install tavily-python`（或 `npm install @tavily/core`）
3. `client.search(query=..., include_answer=True)` 返回 LLM 直接能用的片段

---

## 简介

Tavily Search 是为 AI agent 和 RAG 设计的搜索 API。不像 Google Custom Search 或 Bing API，Tavily 返回精选的内容片段直接喂 LLM —— 不是要再去 scrape 的 URL 列表。可选的 `include_answer` 给出综合答案。适合需要新事实、引用、实时信息的 AI agent。兼容 Tavily REST API / Python / TypeScript SDK / MCP server。装机时间 2 分钟。

---

### Hello world

```python
from tavily import TavilyClient

client = TavilyClient(api_key=os.environ["TAVILY_API_KEY"])

response = client.search(
    query="What is the latest version of Python?",
    search_depth="advanced",
    include_answer=True,
    include_raw_content=False,
    max_results=5,
)

print(response["answer"])
# "As of October 2024, the latest stable version of Python is 3.13.0..."

for r in response["results"]:
    print(f"{r['title']} — {r['url']}")
    print(r["content"][:200])
```

### 搜索深度

| 模式 | 用途 | 成本 |
|---|---|---|
| `basic` | 快速事实查询 | 1 credit |
| `advanced` | 多源研究、RAG | 2 credits |

advanced 模式爬更多源 + 重排，答案质量更好，延迟和成本略高。

### 按域名过滤

```python
# 白名单
response = client.search(
    query="Latest LangChain release notes",
    include_domains=["python.langchain.com", "github.com"],
)

# 黑名单
response = client.search(
    query="Best vector databases",
    exclude_domains=["medium.com"],  # 避开 SEO blogspam
)
```

### 当 MCP

```json
{
  "mcpServers": {
    "tavily": {
      "command": "npx",
      "args": ["-y", "tavily-mcp"],
      "env": { "TAVILY_API_KEY": "tvly-..." }
    }
  }
}
```

Claude Code / Cursor 直接调 `tavily_search` / `tavily_extract` / `tavily_crawl`。

---

### FAQ

**Q: Tavily 免费吗？**
A: 免费 —— 免费档每月 1000 API credit，不要信用卡。付费档加更高配额和团队功能。价格见 tavily.com。

**Q: Tavily 跟 SerpAPI 调 Google 啥区别？**
A: SerpAPI 返回 Google 的 HTML 自然结果，你自己 scrape + 清洗。Tavily 已经做了清洗、排序、可选的综合。Tavily 为 LLM 消费打造；SerpAPI 为 SERP scraping 打造。

**Q: 能配 LangChain 用吗？**
A: 能 —— `langchain_community.tools.tavily_search.TavilySearchResults` 是 LangChain 内置工具。LlamaIndex / CrewAI / Pydantic AI 同样。

---

## 来源与感谢

> Built by [Tavily](https://github.com/tavily-ai). Commercial product with free tier.
>
> [tavily-ai/tavily-python](https://github.com/tavily-ai/tavily-python) — ⭐ Active


---
Source: https://tokrepo.com/en/workflows/tavily-search-search-api-built-for-ai-agents
Author: Tavily