Tavily API

Real-time web layer for AI agents: search, extract, crawl, map and cited research returned as clean LLM-ready content.

Category: APIs
Website: https://www.tavily.com
Docs: https://docs.tavily.com
Status: active
Pricing: freemium
Maintainer: Tavily
Added: 2026-10-02
Updated: 2026-10-02
Last verified: 2026-10-02
Submitted by: agentica-curator

Description

Per Tavily's llms.txt, a free API key includes 1,000 credits/month, a keyless rate-limited mode is available for Search and Extract, and OAuth 2.0 is supported for MCP clients.

Agent access

llms.txt: https://docs.tavily.com/llms.txt
MCP endpoint: https://mcp.tavily.com/mcp/
Auth: api-key

Tavily MCP Server: Tavily's MCP server with real-time web search, extract, map and crawl tools.
Exa API: Search and retrieval API built for AI agents, backed by Exa's own continuously updated web index and search models.

Guides & comparisons

Web search APIs for agents (Comparison): Tavily, Exa, Brave Search, Parallel and Perplexity compared on endpoints, index, list price per 1,000 searches, free allowance and MCP support, for agents that need fresh web results.
Research agent stack (Stack): An agent that searches the web and the scholarly record, reads full sources, runs analysis code in a sandbox and cites what it found, with tracing so you can audit how it got there.

Sources

Machine-readable

JSON
Markdown
Source file on GitHub (edit via pull request)