tavily-python
Python wrapper for the Tavily API
Decision gist · record as of 2026-08-14
Yes. The package is actively maintained, has low install friction, carries no security vulnerabilities, and uses a permissive MIT license. It is well-suited for developers building web-aware applications, RAG systems, or research automation. The keyless mode lets you try it immediately; an API key unlocks the full feature set. Install if you need programmatic web search, extraction, or research capabilities.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires a Tavily API key for most endpoints (search, extract, crawl, map, research); keyless mode available for search() and extract() only with rate limits.
- Low friction installation with a pure-Python wheel.
- Active maintenance with recent commits and steady releases.
License · maintenance · safety
permissive license (permissive) — MIT license (permissive). No restrictions on commercial or proprietary use; you may modify and distribute freely as long as you include the license notice.
last release 2026-07-30 (15 days) · last repo commit 2026-07-30 · 1,359 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 7,128,214 downloads/mo, #1,781 on PyPI
Alternatives
Verify before relying
pip install tavily-python
from tavily import TavilyClient
client = TavilyClient(api_key="tvly-YOUR_API_KEY")
response = client.search("Who is Leo Messi?")
print(response)- Whether the keyless mode rate limits are sufficient for typical development workflows.
- Performance characteristics and latency for large-scale crawl or research operations.
- Cost structure and pricing tiers for API key holders.
What it is and what it does
Tavily Python is a client library that wraps the Tavily web intelligence API, letting you call search, content extraction, website crawling, site mapping, and research report generation from Python without writing HTTP requests directly. It handles authentication, response parsing, and error handling for you, and includes a keyless mode for trying search and extract without signing up.
The SDK is designed for integration into applications that need to gather web data programmatically—feeding context into RAG systems, answering questions with current web information, extracting structured content from multiple URLs, or building research workflows. It depends on requests, tiktoken, and httpx for HTTP transport and token counting, and requires Python 3.8 or later.
Use it for
- Feed live web search results as context into a RAG or LLM application to ground answers in current information.
- Extract raw text and images from a batch of URLs for content analysis or data collection pipelines.
- Crawl a website with natural-language instructions to gather pages matching specific criteria.
- Generate structured research reports on a topic with automatic source gathering and citation formatting.
- Build a Q&A system that retrieves and synthesizes answers from the web in a single API call.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
The package is actively maintained, has low install friction, carries no security vulnerabilities, and uses a permissive MIT license. It is well-suited for developers building web-aware applications, RAG systems, or research automation. The keyless mode lets you try it immediately; an API key unlocks the full feature set. Install if you need programmatic web search, extraction, or research capabilities.
Install
tavily-python on PyPI
Before you install
Low friction installation with a pure-Python wheel. Active maintenance with recent commits and steady releases. Depends on requests, tiktoken, and httpx—all stable, widely-used libraries with no known friction.
Requires a Tavily API key for most endpoints (search, extract, crawl, map, research); keyless mode available for search() and extract() only with rate limits.
License in practice
MIT license (permissive). No restrictions on commercial or proprietary use; you may modify and distribute freely as long as you include the license notice.
Quickstart
pip install tavily-python
from tavily import TavilyClient
client = TavilyClient(api_key="tvly-YOUR_API_KEY")
response = client.search("Who is Leo Messi?")
print(response)Verify before relying
- Whether the keyless mode rate limits are sufficient for typical development workflows.
- Performance characteristics and latency for large-scale crawl or research operations.
- Cost structure and pricing tiers for API key holders.
Package facts
| License | permissive license permissive |
| Python support | Supports the current Python release >=3.8 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 3 packagesrequeststiktokenhttpx |
| Maintenance | Actively maintained 15 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 7,128,214 / month, #1,781 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | License :: OSI Approved :: MIT LicenseOperating System :: OS IndependentProgramming Language :: Python :: 3 |
Evidence: tavily_python-0.7.27-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “website crawler python”
- tavily-pythonPython SDK for the Tavily API, providing web search, content…
- spider-clientPython SDK for the Spider Cloud API that enables website scraping,…
- LinkCheckerLinkChecker validates links across websites by crawling pages and…
Give your agent the search over MCP, or paste the wish link into any chat.
More WWW/HTTP packages
urllib3 is an HTTP client library that provides thread-safe connection pooling, SSL/TLS verification, multipart file uploads, request retries, compression support, and proxy handling for Python applications.
Requests is a Python HTTP library that simplifies sending HTTP/1.1 requests with automatic handling of headers, authentication, cookies, and response parsing.
h11 is a pure-Python HTTP/1.1 protocol implementation that handles parsing and serializing HTTP messages without any built-in I/O, letting you integrate it with any network layer you choose.
HTTPX is a fully featured HTTP client library for Python that provides both sync and async APIs, with support for HTTP/1.1 and HTTP/2, plus an integrated command-line client.
Install it if you are building new projects or modernizing existing ones that rely on HTTP.
A minimal low-level HTTP client library that sends HTTP requests with thread-safe and task-safe connection pooling, supporting HTTP/1.1, HTTP/2, proxies, and both sync and async interfaces.
aiohttp is an async HTTP client and server framework built on asyncio, supporting both WebSockets and middleware-based routing for building concurrent web applications.
Install it if you need async HTTP client or server capabilities in asyncio-based applications.
See also langchain-tavily · tavily-cli · Crawl4AI · firecrawl · scrapegraph-py · firecrawl-py · seltz · serpapi · valyu · tako-sdk