Firecrawl Changelog

Firecrawl v2.9.0 includes browser interaction via /interact, new scrape formats, smarter PDF handling, two new SDKs, and reliability fixes.

Key Features:

• Browser Interaction via /interact — Scrape a page, then call /interact to click buttons, fill forms, navigate, or extract dynamic content using natural language or Playwright/Bash code. Sessions persist across calls with live view URLs and reusable browser profiles.
• Query Format — Pass natural-language prompts to /scrape and get direct answers in data.answer.
• Audio Format — Request audio output from any scrape as a field on the document.
• onlyCleanContent Parameter — Strip navigation, ads, and non-semantic content from markdown output.
• PDF Parsing Modes — Choose fast, auto, or ocr parsing with maxPages option for fine-grained extraction control.
• Java & Elixir SDKs — Official SDKs with full v2 API support, joining JS, Python, Go, and Rust.

Introduce the new /interact endpoint that turns any scrape into a live browser session where agents can click, type, and navigate using natural language.

Key Features:

• Natural Language Control — Describe what you want in plain English; the agent clicks, types, scrolls, and extracts data automatically without selectors or scripts.
• Live Browser Sessions — Every session includes a live URL you can embed, share, or interact with in real time for debugging and demos.
• Persistent Profiles — Log in once and pick up where you left off with cookies and localStorage carrying across scrapes with named profiles.
• Full Playwright Control — Switch to code mode and run Playwright (Node.js or Python) or Bash for precision control.
• Session Reuse — Chain multiple interact calls on the same scrape with the browser maintaining state between calls for complex multi-step workflows.

Full support for core endpoints including scrape, search, and crawl. Works with Maven, Gradle, and Java 17+.

Key Features:

• Maven & Gradle Ready — Drop into any Java project via JitPack with standard dependency management.
• Java 17+ Support — Built for modern Java environments.
• Core Endpoint Coverage — Scrape, search, crawl, map, and agent endpoints all supported.

New PDF parsing engine delivers 3x faster parsing and significantly improved reliability. Rebuilt in Rust, it automatically adapts to any PDF from clean text files to scanned reports and complex layouts.

Key Features:

• Rust-Based Parser — High-performance engine built in Rust delivers up to 3x faster parsing, reducing latency in data ingestion and embedding workflows.
• Three Parsing Modes:
  • fast — text-only parsing for maximum performance.
  • auto — new default; starts in fast mode and automatically falls back to OCR when needed, intelligently detecting edge cases like embedded images, graphs, multi-column layouts, and unusual text encodings.
  • ocr — forces OCR parsing for fully image-based or scanned documents.
• Built for Production Reliability — Extensively tested across thousands of real-world PDFs for consistent, accurate extraction.

Browser Sandbox gives agents a secure, fully managed browser environment for interactive web automation with no local setup, Chromium installs, or driver compatibility issues. Each session runs in an isolated, disposable sandbox that scales without infrastructure management.

Key Features:

• Browser Sandbox — Launch secure, isolated browser sessions with Python, JavaScript, and bash execution. Pre-installed with agent-browser CLI and Playwright.
• Multi-Language Support — Execute Python, JavaScript, or bash code remotely via API, CLI, or SDK with instant results.
• agent-browser Integration — Pre-installed CLI with 40+ commands for AI agents to write simple bash commands instead of complex Playwright code.
• Live View & CDP Access — Watch sessions in real time via embeddable stream URL or connect own Playwright instance over WebSocket.
• Session Management — Configurable TTL controls, parallel sessions (up to 20 concurrent), and automatic cleanup. 2 credits per browser minute with 5 minutes free.

Significantly improved logo extraction accuracy for Branding Format v2, the endpoint for extracting brand identities from websites.

Key Features:

• Significantly improved logo detection — More reliable logo extraction with fewer false positives and better handling of edge cases like logos embedded in background images.
• Works with modern site builders — Branding Format now properly detects logos built with Wix, Framer, and other drag-and-drop platforms generating complex or non-semantic HTML.
• Built for AI agents and developers — Captures colors, typography, spacing, and UI components in structured format to power AI agents and apps.

Firecrawl v2.8.0 brings major improvements to agent workflows, developer tooling, and self-hosted deployments across the API and SDKs.

Key Features:

• Parallel Agents — Execute thousands of /agent queries simultaneously with automatic failure handling and intelligent waterfall execution. Powered by Spark 1 Fast for instant retrieval, automatically upgrading to Spark 1 Mini for complex queries.
• Firecrawl Skill — Enables agents to use Firecrawl for web scraping and data extraction.
• Firecrawl CLI — Command-line interface with full scrape, search, crawl, and map support.
• Spark Model Family — Three new models: Spark 1 Fast for instant retrieval, Spark 1 Mini for complex research queries, and Spark 1 Pro for advanced extraction tasks.
• Agent Enhancements — Webhook support, model selection, and new MCP Server tools for autonomous web data gathering.

Bringing parallel processing to /agent, letting you batch hundreds or thousands of queries simultaneously. What took hours of sequential queries now completes in minutes with automatic failure handling and parallel execution.

Key Features:

• Parallel Batch Processing — Run thousands of /agent queries simultaneously to enrich companies, research competitors, or build datasets at scale.
• Intelligent Waterfall — Tries instant retrieval first, then automatically upgrades specific cells to full agent research (Spark One Mini) only when needed.
• Real-Time Spreadsheet Interface — Work in familiar CSV format with instant visual feedback as cells populate in real-time.
• Zero Configuration — Input data schema, write one prompt, hit run without workflow building.
• Predictable Pricing — 10 credits per cell with Spark-1 Fast.

Introducing the Firecrawl Skill and CLI, a new way for AI agents to reliably access real-time web data. With a single install, agents like Claude Code, Antigravity, and OpenCode can access Firecrawl endpoints including scrape, search, crawl, and map.

Key Features:

• One-Command Install — Install the skill with a single command to teach agents how to authenticate and use all of Firecrawl's endpoints.
• Real-Time Web Data at Runtime — Agents can pull fresh, full-page content from docs, product pages, pricing, and articles exactly when needed.
• Context-Efficient for Agents — Uses a file-based approach for context management and bash methods for efficient search and retrieval.
• Works Across Complex & Dynamic Sites — Powered by Firecrawl's custom browser stack for reliable extraction from large, JavaScript-heavy sites.
• Proven, Best-in-Class Coverage — Backed by benchmark results showing >80% coverage across real-world evaluations.

Major release with enterprise features and platform improvements.

Key Features:

• ZDR Search Support — Enterprise customers can now search with Zero Data Retention enabled end-to-end.
• Partner Integrations API — Available in closed beta for native integrations in partner products.
• Improved Branding Format — Better detection and support across all platforms.
• Faster Screenshots — Enhanced viewport and full page screenshots with improved speed and accuracy.
• Self-hosted Improvements — Significant enhancements for deployments and infrastructure.
• Performance Enhancements — Platform-wide improvements for better user experience.

Major release with unified billing, enhanced features, and significant reliability improvements.

Key Features:

• Unified Billing Model — Credits and tokens merged into single system. Extract now uses credits (15 tokens = 1 credit), existing tokens work everywhere.
• Enhanced Branding Format — Full support across Playground, MCP, JS and Python SDKs.
• Reliability and Speed Improvements — All endpoints significantly faster with improved reliability.
• Instant Credit Purchases — Buy credit packs directly from dashboard without waiting for auto-recharge.
• Improved Markdown Parsing — Enhanced markdown conversion and main content extraction accuracy.
• Change Tracking — Faster and more reliable detection of web page content updates.
• Core Stability Fixes — Fixed core stability issues, PDF timeouts, and improved error handling.

Major release delivering the highest quality and most comprehensive web data API with two major infrastructure improvements: a new Semantic Index and a completely custom browser stack.

Key Features:

• Semantic Index — New infrastructure improvement for better understanding and extraction of web content.
• Custom Browser Stack — Completely redesigned browser infrastructure for improved reliability and performance.
• Benchmark Results — Represents a significant leap forward in web data extraction quality and comprehensiveness.
• Open-Sourced Benchmarks — Released scrape-evals, a reproducible framework for testing web scraping engines on 1,000 real URLs.

Major release featuring open-source scrape-evals benchmark testing 13 web scraping engines on 1,000 URLs, improved full-page extraction with enhanced browser stack, semantic index for faster retrieval of fresh or previously indexed data, 5x cheaper search with auto-recharge credit packs, smarter concurrency and crawl architecture for improved throughput and reliability, and Excel (.xlsx) scraping support for spreadsheets and CSV files.

New PDF search category for filtering documents via v2/search endpoint, 10x improved semantic crawling with better accuracy for prompt-based crawling, new x402 search endpoint via Coinbase integration, fire-enrich v2 AI-powered data enrichment example, enhanced crawl status with real-time updates and robots.txt warnings, and 20+ self-host stability and functionality improvements.

YouTube transcript support, ODT and RTF parsing support, ~50x faster Docx parsing, enterprise auto-recharge, playground UX improvements, and self-hosting improvements.

MCP version 3 with stable cloud support via HTTP Transport and SSE modes, webhook signatures and extract support with event failure tracking, 15x faster Map endpoint with expanded URL support, search reliability improvements, API key-based usage tracking, support for additional locations (CA, CZ, IL, IN, IT, PL, PT), queue status endpoint, and maxPages parameter for v2 scrape API PDF parsing.

Search categories filter (github for repositories and code, research for academic websites like arXiv, Nature, IEEE, PubMed), image extraction support in v2 scrape endpoint, data-* attribute scraping, hash-based routing for crawl endpoints, improved Google Drive scraping for TXT, PDF, and Sheets, PDF title extraction and metadata, and Map endpoint support for up to 100k results.

Faster by default with 2-day maxAge caching and sensible defaults (blockAds, skipTlsVerification, removeBase64Images), new "summary" format for concise page content, updated JSON extraction with object format (old "extract" renamed to "json"), enhanced screenshot options using object form, new search sources for news and images, and smart crawling with natural-language prompts that auto-derive paths and limits with crawl-params-preview endpoint.

SSO for enterprise, improved scraping reliability, search params added to activity logs, FireGEO open-source example, and over 50 PRs merged for bug fixes and improvements.

Authenticated scraping (waitlist available), zero data retention for enterprise, improved p75 speeds, new MCP version with maxAge parameter and better tool calling, open-source Open Researcher example, and numerous additional improvements.