Tavily website screenshot

Tavily

Tavily is a web access API platform optimized for LLMs and AI agents. It exposes a unified REST surface for real-time web search, page content extraction, site crawling, sitemap mapping, and AI-driven research tasks. The platform emphasizes low-latency search with a 180ms p50 on the search endpoint, a 99.99% uptime SLA, and built-in content validation safeguards. Tavily ships Python and JavaScript SDKs and integrates cleanly with major agent frameworks and LLM providers such as OpenAI, Anthropic, and Groq. Used by more than a million developers, it is trusted by enterprise customers including Databricks, IBM, JetBrains, MongoDB, and AWS.

1 APIs 0 Features
SearchWeb SearchAI AgentsLLMsExtractCrawlSitemapResearchRESTLangChainLlamaIndexReal-Time

APIs

Tavily Web API

The Tavily Web API offers a unified set of endpoints for AI agents to search the web, extract page content, crawl sites, map sitemaps, and run AI research tasks. Endpoints are R...

Collections

Pricing Plans

Tavily Plans Pricing

1 plans

PLANS

Rate Limits

Tavily Rate Limits

2 limits

RATE LIMITS

FinOps

Tavily Finops

FINOPS

Resources

🔗
Website
Website
🔗
Documentation
Documentation
📰
Blog
Blog
👥
GitHubOrganization
GitHubOrganization
💰
Pricing
Pricing
📜
TermsOfService
TermsOfService
📜
PrivacyPolicy
PrivacyPolicy
🔗
Community
Community
🔗
X
X
🔗
LinkedIn
LinkedIn
👥
YouTube
YouTube
🔗
LlmsText
LlmsText

Sources

Raw ↑
opencollection: 1.0.0
info:
  name: Tavily Web API
  version: 1.0.0
request:
  auth:
    type: bearer
    token: '{{bearerToken}}'
items:
- info:
    name: Search
    type: folder
  items:
  - info:
      name: Web search
      type: http
    http:
      method: POST
      url: https://api.tavily.com/search
    docs: Run a real-time web search query.
- info:
    name: Extract
    type: folder
  items:
  - info:
      name: Extract page content
      type: http
    http:
      method: POST
      url: https://api.tavily.com/extract
    docs: Pull clean text and metadata from one or more URLs.
- info:
    name: Crawl
    type: folder
  items:
  - info:
      name: Crawl website
      type: http
    http:
      method: POST
      url: https://api.tavily.com/crawl
    docs: Crawl a website with natural-language instructions and constraints.
- info:
    name: Map
    type: folder
  items:
  - info:
      name: Map site structure
      type: http
    http:
      method: POST
      url: https://api.tavily.com/map
    docs: Generate a structured map of a site's pages and structure.
- info:
    name: Research
    type: folder
  items:
  - info:
      name: Run AI research task
      type: http
    http:
      method: POST
      url: https://api.tavily.com/research
    docs: Run an AI-driven research task that aggregates, ranks, and cites sources.
bundled: true