Tavily
by Tavily
One search API built for LLM agents and RAG
Tavily is a web search and data-access API purpose-built for LLM agents and RAG, returning real-time, token-efficient, source-attributed results.
Tavily provides a single, secure API that connects AI agents and LLM applications to the web. Its core capabilities are Search (LLM-optimized, ranked, concise web results), Extract (pull clean content from specific URLs), Crawl (traverse a site's pages), and Map (discover a site's structure and URLs), with responses designed to be token-efficient and source-attributed for grounding and RAG. Tavily grew out of the popular open-source GPT Researcher project created by founder Rotem Weiss, and the New York-based company raised $25M (a $20M Series A led by Insight Partners, with Alpha Wave Global) announced in 2025. It offers official Python and JavaScript/TypeScript SDKs plus integrations for LangChain, the Vercel AI SDK, and an MCP server.
At a Glance
- Category
- AI Agents & Orchestration
- Pricing
- Usage-based, Free tier, Subscription, Enterprise
- Target Market
- Developers, Startups, Enterprise
- Founded
- 2023
- Headquarters
- New York, USA
Key Features
- ✓Search API
LLM-optimized web search returning ranked, concise, source-attributed results in real time.
- ✓Extract
Retrieve clean, structured content from one or more specific URLs.
- ✓Crawl
Traverse a website's pages to gather content across a site.
- ✓Map
Discover a site's structure and enumerate its URLs.
- ✓Agent-ready responses
Token-efficient, citation-backed output designed for direct use in LLM prompts and RAG.
Capabilities
Use Cases
- •Agent web grounding
Connect AI agents to real-time web data through one secure API to reduce hallucinations.
- •RAG context retrieval
Fetch fresh, relevant, cited content to augment retrieval pipelines.
- •Automated research
Power research assistants (e.g., in the GPT Researcher lineage) with search and extraction.
Ideal For
Best For
- ✓Grounding LLM agents with real-time web data
- ✓RAG pipelines needing fresh, cited context
- ✓Building automated research assistants
Not Ideal For
- ✗Use cases needing a full browser-automation / form-interaction scraper
Integrations
Deployment
Pricing
Researcher (Free)
$0/mo
- ✓1,000 API credits/month
- ✓No credit card required
- ✓Email support
Pay As You Go
$0.008 per credit
- ✓Pay only for what you use
- ✓No minimum commitment
- ✓Cancel anytime
Project
From custom (min 4,000 credits/mo)
- ✓Higher rate limits
- ✓Scalable monthly credits
- ✓Email support
Enterprise
Custom
- ✓Custom API volume and rate limits
- ✓Enterprise support and SLAs
- ✓Security & privacy provisions
API credit-based. Free 'Researcher' tier includes 1,000 credits/month; Pay As You Go is $0.008 per credit; the 'Project' plan starts at a 4,000 credits/month minimum with a usage slider; Enterprise is custom-priced. A free student plan is also offered.
Connect
Stay Ahead of the Curve
Weekly enterprise AI insights for technology leaders. No spam, no vendor pitches—unsubscribe anytime.
SubscribeRelated Products
Sema4.ai
Enterprise AI agents for knowledge work, running natively in your Snowflake or cloud account
Sapiom
Agent infrastructure that routes, runs and meters AI agents in production
Itential FlowAI
Governed AI agents for network and infrastructure operations, with deterministic execution and full audit trails
OpenAI Presence
Deploy production-grade AI voice and chat agents with enterprise policies, guardrails and evals