Introducing /parse. Convert PDFs, Word docs, or spreadsheets into clean data for AI agents 5x faster. Try it now →
Nicolas Camara
Update (as of 4th Feb, 2026): Introducing Agent: The Next Evolution of Extract. We’re launching /agent — the successor to /extract. It’s faster, more reliable, and doesn’t require URLs. Just describe what you need and let the AI agent find and extract the data for you. Try Agent now.
Welcome to Day 6 of Firecrawl's Launch Week! We're excited to introduce v1 support for LLM Extract.
Introducing the Extract Format
LLM extraction is now available in v1 under the extract format. To extract structured from a page, you can pass a schema to the endpoint or just provide a prompt.
Output
Extracting without schema (New)
You can now extract without a schema by just passing a prompt to the endpoint. The LLMs choose the structure of the data.
Learn More
Learn more about the extract format in our documentation.
Nicolas Camara @nickscamara_
CTO of Firecrawl
About the Author
Nicolas Camara is the Chief Technology Officer (CTO) at Firecrawl. He previously built and scaled Mendable, one of the pioneering "chat with your documents" apps, which had major Fortune 500 customers like Snapchat, Coinbase, and MongoDB. Prior to that, Nicolas built SideGuide, the first code-learning tool inside VS Code, and grew a community of 50,000 users. Nicolas studied Computer Science and has over 10 years of experience in building software.
More articles by Nicolas Camara
Using OpenAI's Realtime API and Firecrawl to Talk with Any WebsiteExtract website data using LLMsAnnouncing Deep Research APIFirecrawl + Lovable - Build Web Data Apps Without Writing CodeFirecrawl + n8n: Bring Real-Time Web Data Into Your AI WorkflowsGetting Started with Grok-2: Setup and Web Crawler ExampleLaunch Week I / Day 6: LLM Extract (v1)Launch Week I / Day 7: Crawl Webhooks (v1)OpenAI Swarm Tutorial: Create Marketing Campaigns for Any WebsiteBuild a 'Chat with website' using Groq Llama 3FOOTER
The easiest way to extract
data from the web
data from the web