← Back to all tools

Tavily

Web search API designed for AI agents — 1,000 free credits/mo, $0.008/credit PAYG

tavily.com ↗
APIFree tier
Visit site

Overall score

2.8/ 5
SME Fit3/5usage-metered pricing + free tier
JTBD4/5solid named JTBD
Integration3/5API
Trust3/5growing, founded 2023
Quality1/5no public rating
Compliance2/5compliance unknown

About

Tavily is a web search API built specifically for LLM agents — returns clean, citation-friendly content optimized for grounding rather than the chunked snippet output Bing/Google APIs return. Default search backend in many coding agents (Cursor, Claude Code) and RAG pipelines. Pricing is credit-based with a generous free tier for solo builders.

Best for: Anyone building an agent or RAG pipeline that needs to ground answers in current web information. Free tier (1,000 credits/mo) covers most solo builds; pay-as-you-go at $0.008/credit means a 100K-search month is $800 if you grow there.

Pricing

TierMonthlyAnnual /moBillingNotes
ResearcherFreeFreeflat1,000 API credits/mo;Email support;No credit card required · Free forever. Genuinely usable for solo builders and POCs.
Pay-as-you-go——usage$0.008/credit;Flexible usage model;Email support · No monthly minimum. Best when usage is variable.
Project——flat4,000 API credits/mo;Higher rate limits;Email support · Monthly subscription. Pricing displayed dynamically on Tavily's site.
Enterprise——flatCustom API calls;Custom rate limits;Enterprise-grade support and SLAs · Contact sales for custom pricing.

Key features

  • Search API designed for LLM grounding (clean text, citations)
  • 1,000 free credits/mo on Researcher tier
  • $0.008/credit pay-as-you-go
  • Project tier with 4,000 credits/mo and higher rate limits
  • Free student tier
  • Native LangChain, LlamaIndex, Vercel AI SDK integrations
  • Used as default search in many coding agents

Integrations

LangChainLlamaIndexVercel AI SDKOpenAI Agents SDK

Trust & compliance

Stage range
—
Founded
2023
Status
active
SOC 2
unknown
GDPR
unknown
Data residency
unknown
External rating
—
Last verified
May 2026

Reviews

Be the first to share your experience.

Related tools in agent_infra

See all ai agent infrastructure →
  • Ollama3.6

    The easiest way to run open language models locally

  • Pinecone3.4

    Reference vector database for RAG and semantic search — Starter tier is free up to 2GB

  • Hugging Face3.3

    The model hub the open-source AI ecosystem runs on — free Spaces, $9 PRO, $20/user Team

  • Replicate3.2

    Run, fine-tune, and deploy AI models with one line of code

Pairs well with