Tavily

60/100

Search + extract API purpose-built for LLMs and agents.

tavily.com

// scorecard · 60/100

verified 1mo ago

methodology →

Agent-readiness32/35

Agent registration (api_key)6/9

Public API5/5

OpenAPI spec9/9

MCP server9/9

llms.txt3/3

Reliability & performance0/15

Actively maintained—

Production-ready0/4

Updated recently—

Pricing12/13

Itemized public pricing6/6

Free tier / trial4/4

Free-tier generosity2/3

Docs & DX2/12

Docs quality—

Public API2/2

Quickstart / examples0/2

Security & compliance10/12

SOC 26/6

ISO 270012/2

GDPR0/2

Security / trust page2/2

Openness4/10

Open source0/6

Open / un-gated API4/4

Company maturity0/3

Company size—

Years operating—

// rankings · cost per standard workload

#4 in Web Search$500/ 100k queries

Growth $500/mo = 100k credits (1 cr/basic search)

docs.tavily.com

// overview

Tavily provides one secure API for real-time web access to connect AI agents to the web, with endpoints for search, extract, crawl, and research. It retrieves live web data, returns structured relevant chunks for models, and includes built-in safeguards to block PII leakage, prompt injection, and malicious sources. It handles 300M+ monthly requests with 99.99% uptime and 180ms p50 latency on /search, and integrates with providers like OpenAI, Anthropic, and Groq.

Best for: AI agents, developers, and enterprises needing real-time web search and retrieval with production safeguards

// pricing

Free tier · generosity 4/5

Includes: 1,000 API credits/month (Researcher/free plan) · No credit card required · Email support

Limits: Credits reset monthly (no stated rollover)

ResearcherFree

1,000 API credits / month
Email support

Pay As You Go$0.008 / credit

Pay only for what you use
Email support

Project$9 / month

4,000 API credits / month
Higher rate limits
Email support

EnterpriseCustom

Custom API calls
Custom rate limits
Enterprise-grade support and SLAs
Enterprise-grade security and privacy

// security & compliance

✓ SOC 2✓ ISO 27001✗ GDPR✗ HIPAA

// features

real-time web search and data retrieval
structured relevant chunks for models
PII detection and blocking
prompt injection and content validation
intelligent caching and indexing
drop-in integration with leading LLM providers