Firecrawl

The Firecrawl Developer Index is now available, covering 70M+ artifacts across READMEs, docs, issues, PRs, and OpenAPI specs with semantic retrieval and metadata filters. It scores 0.63 recall@10 on the open DevDex benchmark, and each result includes stable IDs, URLs, and matched passages in markdown. Available via API at /search/developer, plus CLI, MCP, SDKs, and a companion skill.

Firecrawl Research Index now covers 41M+ life sciences papers across drug discovery, clinical trial, and biology literature, with 90% recall@10 on paper-retrieval evals. The index is now free to use and accessible via API, CLI, MCP, and SDKs.

Firecrawl /search now returns the excerpts that best answer each query from each result, scoring paragraphs, lists, and tables with a custom relevance model. Agents achieve 94.7% on SimpleQA while using 10x fewer tokens than processing full pages — no API changes required.

Defines search queries and a goal, and Firecrawl searches the entire web on a schedule, alerting via webhook or email when something new matches. The goal field filters results to decide which trigger alerts, with a plain-English explanation of relevance.

Firecrawl Research Index searches 3M+ arXiv papers and GitHub code, core endpoints can be accessed without an API key from official clients, and a new redactPII option strips personal data from scraped content. Also ships deterministicJson format and video discovery on any page.

A specialized search index for AI/ML research papers and code, achieving 53.3% recall on arXivQA versus 45.4% for the next best provider, with 3M+ papers and GitHub artifacts refreshed daily.

Enter a URL, describe what you want to track, and /monitor notifies your AI agent via webhook the moment pages or sites change. Use up to 90% fewer LLM tokens by only ingesting what actually changes.

Firecrawl v2.10 ships a new /parse endpoint, Lockdown Mode, Question and Highlights formats, and four new official SDKs (Go, Ruby, PHP, .NET) - plus a long list of reliability and security fixes.

Firecrawl v2.10 ships a new /parse endpoint, Lockdown Mode, Question and Highlights formats, and four new official SDKs (Go, Ruby, PHP, .NET) plus reliability and security fixes.

Highlights is a new format for /scrape that returns the exact sentences, code blocks, and table rows on a page that match your query, all while using up to 100x fewer tokens.

Question is a format for /scrape that returns high-quality, grounded answers from any web page using up to 100x fewer tokens.

Lockdown Mode is a cache-only option for /scrape that keeps security-sensitive requests inside Firecrawl. Set lockdown: true to serve results exclusively from Firecrawl's index, with zero data retention by default.

The /parse endpoint turns documents into clean, structured data for AI agents and RAG pipelines. Powered by a new Rust-based engine that's up to 5x faster, it works across PDFs, Word docs, spreadsheets, and more.

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.

Fire-PDF is a Rust-based parsing engine that converts any PDF - scanned, text-based, or mixed - into structured markdown, up to 5x faster.

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

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