详细内容
🏆 Tavily Research was just ranked #1 on DeepResearch. Join the waitlist now →
Features Use Cases Benchmarks Pricing Enterprise Careers Blog Docs
Connect Your Agent to the Web
Powering the Internet of Agents with fast, secure
and reliable web access APIs.
Trusted by 800k+ developers around the world
\
\
\Features
Introducing our Search API
Unleash production-ready agents with a search API designed for LLMs.
Delivering fast and relevant results that reduce hallucinations and make agents more powerful.
Python
Node.js
{} cURL
1from tavily import TavilyClient 2tavily_client = TavilyClient(api_key="tvly-YOUR_API_KEY") 3response = tavily_client.search("Who is Leo Messi?") 4print(response)
1const { tavily } = require('@tavily/core'); 2const tvly = tavily({ apiKey: "tvly-YOUR_API_KEY" }); 3tvly.search("Who is Leo Messi?") 4 .then(results => console.log(results));
1curl -X POST 'https://api.tavily.com/search' \ 2 -H 'Content-Type: application/json' \ 3 -H 'Authorization: Bearer tvly-YOUR_API_KEY' \ 4 -d '{"query": "Who is Leo Messi?"}'
Plug and play
Simple setup with just two clicks to sign up, get your API key,
and integrate seamlessly into your application.
Real-time web access
Fast, reliable access with high rate limits, accurate results,
and relevant content snippets optimized for AI processing.
Approach
Enhance Your Agentic Workflow
Supercharge your reports with real-time, comprehensive data from across the web, ensuring accuracy and relevance.
Research Assistant
Transform vast amounts of unstructured web data into actionable insights, unlocking new opportunities for decision-making.
Data Enrichment
Empower your chatbots to deliver precise, up-to-date responses by accessing a wide range of information through Tavily’s robust search capabilities.
Chat Assistant
Blazing fast and production-ready.
Tavily is the web layer that supplies enterprise-grade agents with
fast, real-time web data through simple, agent-first APIs.
Benchmarks
Web Search Driven by Research
SimpleQA BenchmarkDocument Relevance BenchmarkGAIA BenchmarkLeetcode 75 BenchmarkDeepResearch Bench
TavilyPerplexity SearchGoogle (SERP)BraveExaAccuracy (%)93.385.982.276.171.2
About this benchmark
OpenAI’s SimpleQA benchmark measures the ability of language models to answer short, fact-seeking questions. It uses a curated set of factual queries designed to test how accurately a model can retrieve and synthesize factual information. Read more about the SimpleQA benchmark here.
Methodology
We ran the full SimpleQA dataset on each provider and used GPT-4.1 to generate predicted answers from the documents retrieved by that provider. These predictions were then graded with SimpleQA’s classifier.
The final accuracy was calculated by dividing the number of correct answers by the total number of questions.
See the full implementation here.
To maintain fairness and ensure documents of similar length were compared across providers, we setinclude_raw_content=False (default),contents.highlights=True, andmax_tokens_per_page=512 for Tavily, Exa, and Perplexity Search, respectively. In addition, we retrieved a maximum of 10 documents per query across all providers.
Resources
Check out our collaboration with DeepLearning.AI
New Course: AI Agents in LangGraph - YouTube
DeepLearningAI
462K subscribers
New Course: AI Agents in LangGraph
DeepLearningAI
Search
Watch later
Share
Copy link
Info
Shopping
Tap to unmute
If playback doesn't begin shortly, try restarting your device.
More videos
More videos
You're signed out
Videos you watch may be added to the TV's watch history and influence TV recommendations. To avoid this, cancel and sign in to YouTube on your computer.
CancelConfirm
Share
Include playlist
An error occurred while retrieving sharing information. Please try again later.
0:00
0:00 / 3:30
•Live
•
Testimonials
Tavily is trusted by AI leaders around the world
We've been using Tavily's Search API to power Athena, our Enterprise AI Data Analyst. The ability
to retrieve accurate, real-time information tailored for AI agents has significantly enhanced Athena’s
research capabilities. Tavily's focus on delivering factual and explicit results aligns perfectly with
our commitment to providing trustworthy and sourced insights to our enterprise clients.
Brendon Geils
Co-Founder of Athena Intelligence
Search is essential for AI assistants. At CopilotKit, we build deeply-integrated AI assistants where search is a critical feature. Tavily's Search API fills this gap, providing accurate, up-to-date information that transforms AI copilots into invaluable productivity tools for our customers from day one.
Atai Barkai
Co-Founder of CopilotKit
Accurate and up-to-date knowledge has become a key component of building many types of LLM-powered apps. Tavily's reliable search APIs have made them an essential partner for LangChain, and our open-source integration with them has been a huge boon to the community as a whole. It's always a pleasure working with the Tavily team!
Jacob Lee
Founding Engineer at Langchain
We've been using Tavily's Search API to power Athena, our Enterprise AI Data Analyst. The ability
to retrieve accurate, real-time information tailored for AI agents has significantly enhanced Athena’s
research capabilities. Tavily's focus on delivering factual and explicit results aligns perfectly with
our commitment to providing trustworthy and sourced insights to our enterprise clients.
Brendon Geils
Co-Founder of Athena Intelligence
Search is essential for AI assistants. At CopilotKit, we build deeply-integrated AI assistants where search is a critical feature. Tavily's Search API fills this gap, providing accurate, up-to-date information that transforms AI copilots into invaluable productivity tools for our customers from day one.
Atai Barkai
Co-Founder of CopilotKit
Accurate and up-to-date knowledge has become a key component of building many types of LLM-powered apps. Tavily's reliable search APIs have made them an essential partner for LangChain, and our open-source integration with them has been a huge boon to the community as a whole. It's always a pleasure working with the Tavily team!
Jacob Lee
Founding Engineer at Langchain
We've been using Tavily's Search API to power Athena, our Enterprise AI Data Analyst. The ability
to retrieve accurate, real-time information tailored for AI agents has significantly enhanced Athena’s
research capabilities. Tavily's focus on delivering factual and explicit results aligns perfectly with
our commitment to providing trustworthy and sourced insights to our enterprise clients.
Brendon Geils
Co-Founder of Athena Intelligence
Search is essential for AI assistants. At CopilotKit, we build deeply-integrated AI assistants where search is a critical feature. Tavily's Search API fills this gap, providing accurate, up-to-date information that transforms AI copilots into invaluable productivity tools for our customers from day one.
Atai Barkai
Co-Founder of CopilotKit
What our users say
When it comes to producing quality reports, it is important to have accurate and up-to-date information as input. That’s why I recommended Tavily for your next research.\
\
\
\
Amine Izrizar\
\
@izrizar-amine I was recommended to try Tavily REST API GPT search engine - and it was amazing and very easy to set up.\
\
\
\
Audi Previo\
\
@audi-previo Connected to the web, to provide the data real time, the best consistent connection can be achieved with the help of Tavily.\
\
\
\
Hrishikesh Yadav\
\
@hrishikesh_ai Tavily is doing such a fantastic job in this space, they deserve 🫡👏\
\
\
\
Pinaki Bhattacharyya\
\
@pinaki-bhattacharyya
Tavily’s role in managing these model interactions, particularly in optimizing tool usage and enhancing the interface, is a key element that can't be overlooked.\
\
\
\
Ganesh Jagadeesan\
\
@ganeshjagadeesan No more SERP fetch → content scraping.\
\
There are already tools that do the same thing such as @tavilyai (my favorite)\
\
\
\
Hide | Make.com expert\
\
@hide_hq My chatbot can answer any question because I integrated the Tavily API.\
\
\
\
Arnav Sharma\
\
@arnavsharma070504
Pricing Plans
Find a plan to power your AI Agents
Researcher
Free/ Month
For new creators
1,000 API credits / month
No credit card required
Email support
Pay As You Go
$0.008/ Credit
For flexible usage
Pay only for what you use
Cancel anytime
Email support
Project
$30/ Month
For enthusiasts
4,000 API credits / month
Slide to adjust plan →
Higher rate limits
Email support
Enterprise
Custom
Includes:
Custom API calls
Custom rate limits
Enterprise-Grade support and SLAs
Enterprise-Grade security and privacy
Custom seats
Free for students
We're dedicated to supporting the pursuit of knowledge
by offering our service at no cost for students.
Faq
Everything you
need to know
If you have any questions, please do not hesitate to reach to our team.
Which Web Access APIs does Tavily offer?
Tavily offers scalable Search, Extract, Map, and Crawl APIs, all built specifically to enrich agents, large language models, and any AI application with instant, up-to-date, cleaned, and structured content from the web. Tavily's powerful AI search engine handles the complexity of the web and gives you simple APIs to integrate into your application.
How is Tavily Search API different from other APIs?
Unlike Bing, Google and SerpAPI, Tavily Search API reviews multiple sources to find the most relevant content from each source, delivering concise, ready-to-use information optimized for LLM context. This focus on RAG and LLMs ensures your AI applications access only the highest-quality data. Tavily Search API is also more affordable and flexible.
What are the key advantages of using Tavily Search API?
- Purpose-built for AI: Designed with AI agents and LLMs in mind, ensuring ideal results for AI workflows like Retrieval Augmented Generation (RAG).
- Customizable: Control the search depth, manage domains.
- Real-time: Retrieves reliable, up-to-date information, ensuring your AI systems have the most relevant data.
- Easy Integration: Simple API setup with support for Python libraries and partnerships with LangChain and LlamaIndex.
- Scalable: Tavily is built to scale as your usage grows, making it a reliable solution for both startups and enterprise customers.
How fast is Tavily Search API?
Speed is a top priority for Tavily. The API typically returns results within seconds (or less!), although complex queries involving extensive data processing may take slightly longer. The system is optimized for efficiency without sacrificing the quality of information.
How will web search information enhance AI applications?
In a dynamic world, pretrained models go stale. Augmenting AI with fresh web data grounds responses in current facts, reducing hallucinations and improving relevance.
- Real-time freshness: Captures breaking news, pricing, docs, and policy changes.
- Grounded answers: Cited sources and extractive snippets increase trust and auditability.
- Wider coverage: Pulls niche and long‑tail information beyond training corpora.
- Better decisions: Up‑to‑date context boosts planning, routing, and tool use.
- Lower hallucinations: Retrieval + attribution encourages factual outputs.
Tavily is an AI search engine built for this purpose. Its fast, secure Search, Extract, and Crawl APIs deliver fresh, high‑quality results with citations, enabling any AI application—chatbots, agents, RAG systems, monitoring, and enrichment pipelines—to consistently benefit from current, reliable web knowledge.
Can I test Tavily Search API before subscribing to a paid plan?
Yes! Tavily offers a free plan that includes limited monthly API calls. This allows you to test its capabilities and explore how it fits into your AI projects before committing to a paid subscription. No credit card is required for the free plan.
Does Tavily Search API provide citations for its results?
Yes, Tavily is committed to transparency. The API includes citations for all the information it retrieves, ensuring you know exactly where the data comes from.
What level of support does Tavily provide?
- Paid subscriptions: Email support via support@tavily.com
- Enterprise Plan: Dedicated, white-glove support with a personal Slack channel, an account manager, an AI engineer for technical assistance, and regular check-ins. We help with debugging, best practices for agent workflows, Retrieval-Augmented Generation (RAG) techniques, and architecture reviews.
When do my monthly API credits reset?
Your API credits reset on the first day of each month, regardless of the billing date. This ensures you start each month with a clean slate of credits to use for your searches.
Where can I find your privacy policy?
Our privacy policy outlines how we handle and protect user data, ensuring full compliance with global data regulations.