# Firecrawl Changelog

Product updates from Firecrawl, newest first. Each entry links to its own markdown page.

- [The Company Enrichment Benchmark](/changelog/company-enrichment-benchmark.md) (October 21, 2026): We tested the leading company enrichment providers on hundreds of U.S. companies to see who delivers accurate data and where information is missing.
- [Free People Data for ChatGPT and Claude](/changelog/people-data-relaunch.md) (October 20, 2026): Give your AI agents access to 270M+ company and people records in Alexandria, with 1,000 free credits a month through the Firecrawl plugin.
- [Firecrawl for Google Cloud](/changelog/google-cloud-launch.md) (October 19, 2026): We're partnering with Google Cloud to give Gemini and ADK agents data from the web and beyond, available on Google Cloud Marketplace.
- [Introducing Fireround](/changelog/fireround.md) (October 15, 2026): Fireround is a new company funding data provider built by Firecrawl. Follow new rounds and research investors in ChatGPT and Claude through Alexandria.
- [Introducing the Marketing Data Pack in Alexandria](/changelog/alexandria-marketing-data-pack.md) (October 13, 2026): Uncover what gets traffic and attention, shape your SEO and GEO strategy, and create content and visuals with better references in ChatGPT or Claude.
- [Introducing Universal Scrape](/changelog/universal-scrape.md) (October 8, 2026): Web pages, files and a growing set of Alexandria providers, all with one Firecrawl API.
- [Fantasy sports data is live in Alexandria](/changelog/alexandria-fantasy-sports.md) (October 6, 2026): Use fantasy rankings, projections, sports betting odds and live news in ChatGPT or Claude to research your next lineup with Firecrawl.
- [People and company enrichment in Alexandria](/changelog/alexandria-people-enrichment.md) (October 1, 2026): Apollo, FullEnrich, and Data Legion give your agents people search, work email lookup, and company enrichment through Firecrawl.
- [Alexandria and the Developer Index are now in ChatGPT and Codex](/changelog/alexandria-chatgpt-codex.md) (September 29, 2026): Use the Firecrawl plugin to search and scrape the web, access 100+ Alexandria data providers, and research code with the Developer Index in ChatGPT and Codex.
- [Alexandria is now in Claude and Claude Code](/changelog/alexandria-claude.md) (September 24, 2026): Give Claude access to 100+ data providers and Firecrawl's specialized indexes alongside live web search and scraping.
- [Introducing Alexandria and our $75M Series B](/changelog/introducing-alexandria-series-b.md) (September 22, 2026): Meet Alexandria, the knowledge library for superintelligence, and our $75M Series B to invest in search and broader access to knowledge.
- [Firecrawl Developer Index](/changelog/developer-index-launch.md) (August 20, 2026): 70M+ primary sources across GitHub repos, docs, issues, and PRs, with the highest recall of any major coding-specific index.
- [Life Sciences in Firecrawl Research Index](/changelog/research-index-life-sciences-launch.md) (August 13, 2026): 41M+ papers across the drug discovery, clinical trial, and biology literature at 90% recall@10, and the whole index is free to use.
- [Introducing our most accurate /search yet](/changelog/improved-search-launch.md) (July 22, 2026): A new custom relevance model returns the excerpts that best answer your query. Agents using Firecrawl /search score 94.7% on SimpleQA, higher than with any other provider tested, while using 10x fewer tokens.
- [Web-scale /monitor](/changelog/web-monitoring-launch.md) (July 1, 2026): Always-on search across the entire web: define a query and goal, and get pinged or webhooked the moment something relevant comes online.
- [v2.11.0 is live](/changelog/v211.md) (June 24, 2026): Firecrawl v2.11.0 ships the Firecrawl Research Index, keyless endpoint access, automatic PII redaction, a deterministicJson format, and video discovery on any page - plus much more.
- [Firecrawl Research Index](/changelog/research-index-launch.md) (June 16, 2026): A specialized research index for AI agents: 3M+ arXiv papers and the GitHub code behind them, with state-of-the-art recall on arXivQA at comparable cost.
- [Introducing /monitor](/changelog/monitoring.md) (May 26, 2026): Notify your AI agent via webhook the moment a page or site changes, and use up to 90% fewer LLM tokens by only ingesting what actually changes.
- [v2.10 is live](/changelog/v210.md) (May 15, 2026): Firecrawl v2.10 ships the /parse endpoint, Lockdown Mode, Question and Highlights formats, and four new official SDKs.
- [Highlights Format](/changelog/highlights-format.md) (May 8, 2026): A new format for /scrape that returns the exact sentences, code blocks, and table rows on a page matching your query, verbatim, with up to 100x fewer tokens than a full scrape.
- [Question Format](/changelog/question-format.md) (May 6, 2026): Ask any web page a question and get a grounded answer with zero hallucinations, using up to 100x fewer tokens than returning the whole page.
- [Lockdown Mode](/changelog/lockdown-mode.md) (April 30, 2026): Serve /scrape results exclusively from Firecrawl's existing index with no outbound traffic and zero data retention by default.
- [Introducing /parse](/changelog/parse.md) (April 28, 2026): Upload PDFs, Word docs, and spreadsheets, and /parse turns them into clean Markdown, JSON, or summaries for AI agents and RAG pipelines.
- [Introducing web-agent](/changelog/open-source-agent.md) (April 16, 2026): Firecrawl `web-agent` is an open framework for building AI agents that search, scrape, and interact with the web. Powered by the same architecture behind our `/agent` endpoint.
- [Introducing Fire-PDF](/changelog/fire-pdf.md) (April 14, 2026): Fire-PDF is Firecrawl's new PDF parsing engine: up to 5x faster, smarter about what hits GPU, and more accurate on complex layouts.
- [v2.9.0 is live](/changelog/v29.md) (April 10, 2026): Browser interaction via /interact, question and audio scrape formats, onlyCleanContent, PDF parsing modes, Java and Elixir SDKs, and dozens of fixes.
- [Introducing /interact - Scrape and Automate Actions With Agents](/changelog/interact.md) (March 25, 2026): Scrape any page, then let your agent click, type, and navigate in natural language or with full Playwright control.
- [Firecrawl Java SDK](/changelog/java-sdk.md) (March 12, 2026): Full support for our core endpoints, including scrape, search, and crawl. Works with Maven, Gradle, Java 17+.
- [Faster, Smarter PDF Parsing](/changelog/pdf-parser-v2.md) (February 26, 2026): Our new PDF parsing engine delivers 3x faster parsing and significantly improved reliability, rebuilt in Rust.
- [Introducing Browser Sandbox](/changelog/browser.md) (February 17, 2026): Firecrawl Browser Sandbox gives your agents a secure, fully managed browser environment
- [Improved Logo Extraction for Branding Format v2](/changelog/branding-format-v2.md) (February 6, 2026): We significantly improved logo extraction accuracy for Branding Format v2.
- [v2.8.0 is live](/changelog/v28.md) (February 3, 2026): Major improvements to agent workflows, developer tooling, and self-hosted deployments across the API and SDKs.
- [Parallel Agents: Extract Web Data at Scale](/changelog/parallel-agents.md) (January 30, 2026): Batch process hundreds or thousands of /agent queries simultaneously with real-time streaming results.
- [Introducing the Firecrawl Skill & CLI](/changelog/skill-cli.md) (January 27, 2026): A new way for AI agents to reliably access real-time web data with a single install.
- [v2.7.0 is here!](/changelog/v27.md) (December 5, 2025): Introducing ZDR Search support, Partner Integrations API, Improved Branding Format and More
- [v2.6.0 available now](/changelog/v26.md) (November 14, 2025): Introducing Unified Billing, Reliability and Speed Improvements, Branding Format, and More
- [v2.5.0 - The World's Best Web Data API](/changelog/v25.md) (October 25, 2025): We now have the highest quality and most comprehensive web data available
- [v2.4.0 is live now](/changelog/v24.md) (October 13, 2025): New PDF search category, 10x better semantic crawling, x402 search endpoint, and open-source upgrades!
- [Firecrawl v2.3.0 is here](/changelog/v23.md) (September 19, 2025): Introducing YouTube transcript support, odt & rtf parsing, 50x faster docx parsing, and more
- [Firecrawl v2.2.0 is here](/changelog/v22.md) (September 12, 2025): Introducing MCP Version 3, Webhooks Signatures, 15x faster map, and more
- [Firecrawl v2.1.0 is here](/changelog/v21.md) (August 29, 2025): Introducing Search Categories, Image Extraction, Data Attribute Scraping, Hash-Based Routing and more
- [Introducing Firecrawl v2](/changelog/v2.md) (August 19, 2025): Firecrawl v2 ships faster scraping by default, a summary format, news and image search, and smart crawling with natural-language prompts.
- [Firecrawl v1.15.0 is here](/changelog/v115.md) (July 18, 2025): Introducing SSO for enterprise, improved scrape reliability, FireGEO example and more
- [Firecrawl v1.14.0 is here](/changelog/v114.md) (July 4, 2025): Introducing authenticated scraping, zero data retention for enterprise, improved speeds, and more
- [Firecrawl v1.13.0 is here](/changelog/v113.md) (June 27, 2025): Introducing AU, FR, DE locations to stealth mode, crawl subdomains, Google Slides scraping, and more
- [Firecrawl v1.12.0 is here](/changelog/v112.md) (June 20, 2025): Introducing Max Concurrency per request, Crawl Entire Domain, Google Docs Scraping, and more
- [Firecrawl v1.11.0 is here](/changelog/index-launch.md) (June 13, 2025): Introducing Firecrawl Index for 5x faster scraping, improved activity logs, and more
- [Introducing Search](/changelog/search-launch.md) (June 3, 2025): Search the web and get full content from results in one API call
- [Firecrawl v1.9.0 Release](/changelog/may16.md) (May 16, 2025): Self-host improvements, MCP enhancements, SDK updates, and performance boosts with increased limits.
- [Enhanced Mode pricing and quality updates](/changelog/may5.md) (May 5, 2025): Enhanced Mode, the proxy option for hard-to-scrape sites, gets a quality upgrade and a pricing change, with guidance on using it as a retry step.
- [Firecrawl Launch Week III – Summary](/changelog/april28.md) (April 28, 2025): Major updates including FIRE-1 agent, Python SDK v2.0, LLMstxt.new, and 20+ new integrations.
- [v1.7.0: Deep Research alpha, concurrent browsers](/changelog/april4.md) (April 4, 2025): Deep Research open alpha with structured outputs, concurrent browsers raise rate limits, /extract no longer needs URLs, and crawl gets a depth option.
- [Concurrent browsers and 5x higher rate limits](/changelog/mar12.md) (March 12, 2025): Rate limits are now expressed as concurrent browsers and raised 5x across plans, with upgrades available for faster throughput.
- [v1.6.0: LLMs.txt API and the MCP server](/changelog/mar7.md) (March 7, 2025): 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.
- [Self-host overhaul: v1.5.0](/changelog/feb20.md) (February 20, 2025): A reworked self-hosting guide, Kubernetes examples, proxy support, SearXNG search and a production Docker image, plus Deep Research alpha and llms.txt.
- [v1.4.4: PDF and image sub-link extraction](/changelog/feb14.md) (February 14, 2025): Extraction now reads PDF and image sub-links with Gemini, scrape validates actions and wait times, and new Gemini crawler and TrendFinder examples ship.
- [Examples week: v1.4.3](/changelog/feb7.md) (February 7, 2025): Open Deep Research, an R1 web extractor, an o3-mini crawler and more examples, with URL deduplication, better blocklists and scrape options for extract.
- [Extract and API improvements: v1.4.2](/changelog/jan31.md) (January 31, 2025): Web search inside extract with enableWebSearch, source tracking, configurable webhook events, a map timeout, and ad blocking on by default.
- [Extract improvements: v1.4.1](/changelog/jan24.md) (January 24, 2025): Extract returns more data, parsing moves from Cheerio to a Rust-based parser, infrastructure is more reliable, and crawl cancellation is more responsive.
- [/extract is now asynchronous](/changelog/jan7.md) (January 7, 2025): Extract requests return a job ID to poll for status. The API stays backwards compatible for 10 days, and the SDKs handle the change for you.
- [v1.2.0: Introducing /search](/changelog/search.md) (January 3, 2025): The new /search endpoint returns web results for any query, with optional full page markdown via scrapeOptions, plus extract fixes and MinerU for PDFs.
- [v1.1.0: geolocation and mobile scraping](/changelog/dec27.md) (December 27, 2024): Geolocation and mobile scraping, 4x faster parsing, better webhooks, credit packs with auto-recharge, iframe support and URL deduplication, plus SDK fixes.
- [Introducing Batch Scrape](/changelog/batch-scrape.md) (October 28, 2024): Scrape many URLs in one request with the new Batch Scrape endpoint, now supported in the Python SDK 1.4 and the Node SDK 1.7.
- [Cancel crawls from the SDKs and faster scrapes](/changelog/oct10.md) (October 10, 2024): Crawl cancellation lands in the Python and Node SDKs, new OpenAI Voice and CRM enrichment examples, improved Docker images and faster scrapes.
- [Crawl reliability fixes](/changelog/sept27.md) (September 27, 2024): Fixes for 500 errors on busy sites, crawl status for pages over 10 MB and undefined screenshots, plus faster recovery when a scraper fails.
- [Introducing Actions](/changelog/actions.md) (September 24, 2024): Click, type, scroll, wait and screenshot before scraping, so dynamic pages give up their data. Available in the REST API and the Node and Python SDKs.
- [Type-safe LLM extract and the Rust SDK](/changelog/sept23.md) (September 23, 2024): End-to-end type safety for LLM extract in the Node SDK, 10x cheaper extraction, Rust SDK v1.0, map limits raised to 1,000 and faster scrapes.
- [Custom header fix for the v1 API](/changelog/sept8.md) (September 8, 2024): Custom request headers are now applied correctly in the v1 API, so the headers you pass on a request reach the page instead of being dropped.
- [Firecrawl v1 is here](/changelog/v1-release.md) (August 29, 2024): Firecrawl v1 brings output formats for /scrape, a new /map endpoint, 2x rate limits, Go and Rust SDKs, teams, API key management and crawl webhooks.

_Canonical HTML: https://www.firecrawl.dev/changelog_

## Site Navigation

### Global Hub
- [Home](/index.md)
- [Pricing](/pricing.md)
- [Blog](/blog.md)
- [Glossary](/glossary.md)
- [Alternatives](/alternatives.md)
- [Tools](/tools.md)
- [Use Cases](/use-cases.md)
- [Integrations](/integrations.md)