Tavily
Search, extract and crawl API for agents, returning cited, LLM-ready content.
Also available as an MCP server
This page covers Tavily the product. To let an agent talk to it over the Model Context Protocol, see the Tavily MCP server.
Why it's indexed
A common default for research agents: one call goes from question to sourced page content, citations included.
Editorial judgment, not a measurement — see our methodology. Listing is never paid for.
At a glance
- Vendor
- Tavily
- Category
- Web Data & Browsing
- License
- Proprietary
- Deployment
- Hosted
- Languages
- Python, TypeScript
- Pricing model
- Free tier · Usage-based · Subscription · Enterprise
Pricing is shown as a model, not a rate. Published rates change without notice — check the vendor's own page before budgeting.
Tags
Also in Web Data & Browsing
Firecrawl
Turns any website into clean Markdown or structured data an agent can use — scrape, crawl and search.
Browserbase
Cloud browsers for agents that need a real session — logins, clicks and forms, not just page text.
Exa
Web search built for agents — returns pages and their content rather than a list of links.