NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
PyPI, #4863 most downloaded on PyPI
Python SDK for Firecrawl, the context API for AI agents: search, scrape, parse, crawl, map, and interact with the web, run Agent and Monitor jobs, and search scientific papers (PubMed, bioRxiv, medRxiv, arXiv)
Latest stable
4.55.0
Last release 15 days ago
04 Nov 2026
Ships on a steady schedule
a new release about every 2 weeks
No release notes found
nothing matched a version
Nothing withdrawn
no release was ever pulled
2 years old
196 releases · first in 2024
Drag across the ruler to compare, or tap a release to open it.
Nothing published for this version
Nothing published for this version
The /llmstxt endpoint allows you to transform any website into clean, LLM-ready text files. Simply provide a URL, and Firecrawl will crawl the site an
The /llmstxt endpoint allows you to transform any website into clean, LLM-ready text files. Simply provide a URL, and Firecrawl will crawl the site and generate both llms.txt and llms-full.txt files that can be used for training or analysis with any LLM.
Docs here: https://docs.firecrawl.dev/features/alpha/llmstxt
The /deep-research endpoint enables AI-powered deep research and analysis on any topic. Simply provide a research query, and Firecrawl will autonomously explore the web, gather relevant information, and synthesize findings into comprehensive insights.
Join the waitlist here: https://www.firecrawl.dev/deep-research
Introducing the Firecrawl MCP Server. Give Cursor, Windsurf, Claude enhanced web extraction capabilities. Big thanks to @vrknetha, @cawstudios for the initial implementation!
See here: https://github.com/mendableai/firecrawl-mcp-server
Full Changelog: v1.5.0...v1.6.0
Full Changelog: https://github.com/mendableai/firecrawl/compare/v1.5.0...v1.6.0
Your coding agent can read these notes before it upgrades. Set up the MCP server →
Turn any site into llms.txt with /llmstxt, join the Deep Research alpha, and give Cursor, Windsurf and Claude web access through the Firecrawl MCP server. Read the full update
Feb 20, 2025
Reworked Guide: The SELF_HOST.md and docker-compose.yaml have been updated for clarity and compatibility
SELF_HOST.md and docker-compose.yaml have been updated for clarity and compatibility/search endpoint (#1193)For the complete details, check out the full changelog.
Full Changelog: https://github.com/mendableai/firecrawl/compare/v1.4.4...v1.5.0
A reworked self-hosting guide, Kubernetes examples, proxy support, SearXNG search and a production Docker image, plus Deep Research alpha and llms.txt. Read the full update
Feb 14, 2025
We’re excited to announce the release of /extract - get data from any website with just a prompt. With /extract, you can retrieve any information from
We’re excited to announce the release of /extract - get data from any website with just a prompt. With /extract, you can retrieve any information from anywhere on a website without being limited by scraping roadblocks or the typical context constraints of LLMs.
No more manual copy-pasting, broken scraping scripts, or debugging LLM calls. - it’s never been easier to enrich your data, create datasets, or power AI applications with clean, structured data from any website.
Companies are already using extract to:
Instead of spending hours manually researching, fixing broken scrapers, or piecing together data from multiple sources, simply specify what information you need and the target website, and let the Firecrawl handle the entire retrieval process.
Specifically, you can:
This versatility translates into a wide range of real-world applications—enabling you to enrich web data for just about any use case.
Curious to try /extract out for yourself? Visit our playground to try out /extract - you get 500,000 tokens for free Dive into our Extract Beta documentation for detailed technical guidance and API reference Want a no-code solution? Connect /extract to thousands of applications through our enhanced Zapier integration
That's all for now! Happy Extracting from the whole Firecrawl team 🔥
Full Changelog: https://github.com/mendableai/firecrawl/compare/v.1.3.0...v1.4.0
Nothing published for this version
feat: new snips test framework (FIR-414) by @mogery in https://github.com/mendableai/firecrawl/pull/1033
Full Changelog: https://github.com/mendableai/firecrawl/compare/v1.2.1...v.1.3.0
Nothing published for this version
Nothing published for this version
Nothing published for this version
Indexes, Caching for /extract, Improvements by @nickscamara in https://github.com/mendableai/firecrawl/pull/1037
We have updated the /extract endpoint to now be asynchronous. When you make a request to /extract, it will return an ID that you can use to check the status of your extract job. If you are using our SDKs, there are no changes required to your code, but please make sure to update the SDKs to the latest versions as soon as possible.
For those using the API directly, we have made it backwards compatible. However, you have 10 days to update your implementation to the new asynchronous model.
For more details about the parameters, refer to the docs sent to you.
Full Changelog: https://github.com/mendableai/firecrawl/compare/v1.2.0...v1.2.1
Changelog: https://www.firecrawl.dev/changelog#/extract-changes
The search endpoint combines web search with Firecrawl’s scraping capabilities to return full page content for any query.
The search endpoint combines web search with Firecrawl’s scraping capabilities to return full page content for any query.
Include scrapeOptions with formats: ["markdown"] to get complete markdown content for each search result otherwise it defaults to getting SERP results (url, title, description).
More info here /v1/search docs
Full Changelog: https://github.com/mendableai/firecrawl/compare/v1.1.1...v1.2.0
The search endpoint combines web search with Firecrawl’s scraping capabilities to return full page content for any query.
Include scrapeOptions with formats: ["markdown"] to get complete markdown content for each search result otherwise it defaults to getting SERP results (url, title, description).
More info here: v1/search docs
Fixed LLM not following the schema in the python SDK for /extract
Fixed schema json not being able to be sent to the /extract endpoint through the Node SDK
Prompt is now optional for the /extract endpoint
Our fork of MinerU is now default for PDF Parsing
Dec 27, 2024
feat(python-sdk): Make API key optional for self-hosted instances by @RutamBhagat in https://github.com/mendableai/firecrawl/pull/990
Full Changelog: https://github.com/mendableai/firecrawl/compare/v1.1.0...v1.1.1
Nothing published for this version
Nothing published for this version
Nothing published for this version
One column per month.