Tavily

Tavily Search API is an AI-friendly real-time web search API designed to empower Large Language Models (LLMs) and AI agents with accurate, up-to-date information. It delivers fast, reliable search results geared for RAG (Retrieval-Augmented Generation) workflows, reducing hallucinations and enabling precise data enrichment for AI applications. Tavily emphasizes easy integration, high scalability, and citation-backed results from trusted sources.

---

How Tavily Works

• Real-time web access tailored for AI agents and LLMs.
• Aggregates results from multiple sources to surface the most relevant, concise information for AI context.
• Provides citations for all retrieved information to ensure traceability and verifiability.
• Supports programmable controls over search depth and domain prioritization.
• Designed to scale with usage, suitable for startups to enterprise deployments.

---

Getting Started

• Install and sign up to obtain an API key. Two-click setup for sign-up and key retrieval.
• Use standard language-specific SDKs (Python, Node.js) or curl for direct API access.
• Make requests to the search endpoint with your query and API key to receive structured results with sources and snippets.

Example (curl):

• curl -X POST 'https://api.tavily.com/search'
  -H 'Content-Type: application/json'
  -H 'Authorization: Bearer tvly-YOUR_API_KEY'
  -d '{"query": "Who is Leo Messi?"}'

Example (Python):

• from tavily import TavilyClient
• tavily_client = TavilyClient(api_key="tvly-YOUR_API_KEY")
• response = tavily_client.search("Who is Leo Messi?")
• print(response)

Example (Node.js):

• const { tavily } = require('@tavily/core');
• const tvly = tavily({ apiKey: "tvly-YOUR_API_KEY" });
• tvly.search("Who is Leo Messi?").then(results => console.log(results));

---

Use Cases

• Real-time information retrieval for AI agents and chat assistants
• Research assistants requiring trustworthy, sourced data
• Data enrichment for chatbots and knowledge bases
• Retrieval-Augmented Generation (RAG) pipelines with high-quality snippets

---

Pricing Plans

• Free / Month (Researcher): 1,000 API credits / month, email support
• Pay As You Go: $0.008 / Credit
• Project: $30 / Month (4,000 API credits / month)
• Enterprise: Custom API calls, higher rate limits, dedicated support, and SLAs
• Special: Free for students

---

Safety, Privacy & Support

• Provides citations for all retrieved data to ensure transparency
• Designed with enterprise-grade security and privacy in mind
• Enterprise support includes dedicated account management and technical assistance

---

Why Tavily

• Purpose-built for AI and LLM workflows
• Customizable search behavior (depth, domains)
• Real-time results with reliable, up-to-date information
• Easy integration with Python, Node.js, and curl; strong partnerships with LangChain and LlamaIndex
• Transparent, sourced information to support trustworthy AI outputs

---

Core Features

• Real-time search tailored for LLMs and AI agents
• Multi-source aggregation with concise, ready-to-use results
• Citation-enabled results for traceability
• Customizable search depth and domain controls
• Easy integration across Python, Node.js, and curl
• High availability with scalable API plans (pay-as-you-go and enterprise)
• Support for RAG workflows and data enrichment
• Partnerships and ecosystem compatibility (LangChain, LlamaIndex)