Tavily

Overview

Tavily is a web search and content extraction API built specifically for AI agents and RAG workflows. It is not a consumer search UI — it is designed to be embedded inside LLM applications. Tavily ships official integrations with Langchain and LlamaIndex and is widely used as the search layer for RAG and agentic apps. In February 2026, Tavily was acquired by Nebius.

Key Features

1. Agent-Optimized Search

Traditional search APIs return a list of URLs and snippets. Tavily instead fetches, parses, and cleans up the top results and returns the body text directly — agents get usable content, not links to scrape.

2. Search + Extract APIs

Search API: search and extract in one call
Extract API: clean extraction from known URLs

Basic Search costs 1 credit per request; Advanced Search costs 2 credits — a transparent pricing model.

3. Official Langchain / LlamaIndex Integrations

Tavily is available as a first-class Retriever / Tool in both frameworks, meaning just a few lines of code to drop it into a RAG or agent pipeline.

4. Domain and Depth Controls

Whitelists, blacklists, search depth (basic/advanced), and HTML content controls give agent developers fine-grained control over behavior.

5. Low Latency (998ms)

Fast enough for interactive agent loops. Ranked 5th overall with an Agent Score of 13.67 in independent benchmarks.

Pricing (2026)

Plan	Monthly	Key Perks
Researcher (Free)	$0	1,000 credits/month
Project	$30	4,000 credits/month
Pay-as-you-go	—	$0.008 per credit
Enterprise	Contact sales	SLA, custom