← Back to directory

Tavily

The web access layer for agents

Visit Tavily

Tavily is a search-and-retrieval API purpose-built for AI agents and RAG pipelines, offering search, extraction, crawling, site mapping, and a higher-level "research task" endpoint that returns LLM-ready results rather than raw SERPs.

Vendor's own claim
data/enrichmentresearch/evidence

Core capabilities

Vendor's own claim
  • Search API returning ranked results with content snippets, relevance scores, and an optional LLM-generated answer
  • Extract API for pulling clean content from a given list of URLs
  • Crawl API that combines mapping and extraction across a domain
  • Map API for discovering a site's page structure
  • Research Task API for multi-step, agentic research with dynamic credit pricing by model tier
  • Real-time data retrieval with intelligent caching
  • Remote MCP server exposing search and extract as tools, with API-key or OAuth auth

API & agent surface

From official docs
Authentication
API key sent as a Bearer token: Authorization: Bearer tvly-YOUR_API_KEY
Base URL
https://api.tavily.com/
Rate limits
Credit costs: basic search 1 credit, advanced search 2 credits; extract 1-2 credits per 5 successful URLs; map 1-2 credits per 10 successful pages; crawl = mapping cost + extraction cost; research tasks 4-110 credits (mini) or 15-250 credits (pro).
Notable endpoints
  • POST /search - web search with optional LLM-generated answer and ranked results
  • POST /extract - content extraction from a given list of URLs
  • POST /crawl - domain crawl combining mapping and extraction
  • POST /map - site structure discovery
  • Research Task endpoint - multi-step agentic research with dynamic credit cost by model tier (mini or pro)
MCP tools exposed
tavily-searchtavily-extract
Machine-readable spec
No OpenAPI link

Official skills & repos

From official docs

Published by the vendor themselves — not community forks.

Pricing

From official docs
PlanPriceIncludedNotable
Researcher (Free)$0/mo1,000 API credits/monthNo credit card required, Email support
Pay As You Go$0.008/creditUsage-based, no monthly allotmentCancel anytime, Email support
ProjectAdjustable monthly rate (usage slider)4,000 API credits/month (base)Higher rate limits, Email support
EnterpriseContact for pricingCustom API call volumeCustom rate limits, SLAs, Enterprise-grade security and privacy

Checked 2026-07-31 against their pricing page. Vendors change pricing without notice.

What is Tavily

Vendor's own claim

It bills per API credit, with different endpoints and depth settings consuming different credit amounts, and exposes the same capabilities through a hosted remote MCP server for AI-assistant clients (Claude Desktop, Claude Code, Cursor, OpenAI clients).

Ideal customer profile

Vendor's own claim

Developers building AI agents, RAG pipelines, or research/automation tools who need live web search and content extraction as an API primitive rather than a consumer search product; the vendor names MongoDB, LangChain, JetBrains, AWS, Mastercard, and IBM as users.

Who should look elsewhere

Our read

Credit pricing is granular and stacks per capability - advanced search costs 2x basic, crawl combines separate mapping and extraction charges, and the Research Task endpoint alone can cost 15-250 credits per call on the pro model - so agentic workflows that chain several of these calls per task can consume the free 1,000-credit/month tier very quickly. No OpenAPI or machine-readable spec was found on the docs site, so teams that want to generate a typed client automatically will need to hand-write one against the REST reference instead.

Tavily alternatives

Our read

APIs that answer a query with retrieved web content, built to be called by an agent rather than read by a person.

Category: Search and research APIs. Membership is decided by 2 stated tests, not by category tags — see them and the full comparison.

Tavily FAQ

Does Tavily publish an OpenAPI spec?

No machine-readable OpenAPI/Swagger spec was found on the docs site at check time; the API reference is presented as per-endpoint documentation pages instead.

Our read
Is there a free tier?

Yes, the Researcher plan gives 1,000 API credits/month at no cost, with no credit card required.

From official docs
How is Tavily priced?

Monthly credit-allotment plans (Free through Project, with an adjustable usage slider) or pay-as-you-go at $0.008/credit, plus custom Enterprise pricing; credit cost varies by endpoint and depth (e.g. advanced search costs 2x basic search).

From official docs
What does a Research Task call cost?

Dynamic pricing depending on query complexity: 4-110 credits on the mini model, 15-250 credits on the pro model.

From official docs
What is the crawl endpoint's pricing model?

Crawl combines the cost of mapping plus extraction on the pages it touches - e.g. crawling 10 pages with basic extraction costs 1 credit (mapping) + 2 credits (extraction) = 3 credits total.

From official docs

Verify before you buy

  • No OpenAPI/Swagger spec was found on the docs site
  • Could not independently confirm the YouTube channel's identity beyond the link appearing in Tavily's own site footer (page content did not render channel details)
  • Numerical API rate limits (requests/second or /minute) beyond the existence of a dedicated Rate Limits reference page
  • No public changelog page was found
  • A machine-readable OpenAPI specification was not included in the reviewed source set.

Need help setting it up?

This page tells you whether Tavily fits. Cheetah builds and runs the system it goes into — enrichment, sequencing, CRM and the joins between them.

Book a call →

The directory stays free. There is nothing gated behind this.