Skip to content

Crawl4AI Web Extractor

AI Platform & Data Crawl4AI 0.9.5 Hardened AMI

Crawl4AI 0.9.5 on Ubuntu 24.04 turns web pages into Markdown and JSON, including pages that need JavaScript. Package 0.2.7 runs a headless browser behind HTTPS on port 8447. First boot creates a TLS certificate and an API token.

Get started View on AWS Marketplace
AMI release
0.2.7 (Crawl4AI 0.9.5)
Recommended
t3.large
Storage
32 GiB+ encrypted gp3
Access
Session Manager or SSH
Released
Oct 24, 2026
Delivery
Amazon Machine Image in your own AWS account

Turn web pages into clean Markdown and JSON for LLM and RAG pipelines.

Built-in headless browser renders pages that need JavaScript.

Private HTTPS API with a per-instance token and certificate, reached through Session Manager.

Quick start

Full guide →
  1. Subscribe
  2. Launch the instance
  3. Run the walkthrough
  4. Call the API

What is on the image

This guide matches Marketplace package 0.2.7 (Crawl4AI 0.9.5). Check the listing for the version currently on offer.

  • Crawl4AI 0.9.5 with a built-in headless browser.
  • HTTPS on port 8447. First boot creates the certificate and the API token and starts the crawler. Do not print the token.
  • A walkthrough, /opt/sushi/docs/demo.sh.
  • Image notes at /opt/sushi/docs/README.md.

t3.large with at least 8 GiB of memory, an encrypted gp3 root volume of 32 GiB, and IMDSv2. Attach AmazonSSMManagedInstanceCore. Leave inbound application ports closed.

Billing

The listing shows a software rate of USD 0.03 per hour on t3.large. Confirm the offer before you subscribe. EC2, EBS, and data transfer are billed separately.

Tutorial

Watch on YouTube.

Where to go next

Upstream project

See the Crawl4AI documentation. Software Sushi packages this image and does not claim upstream or AWS endorsement. Use /opt/sushi/docs/README.md for this build.

Last updated November 1, 2026 · Suggest an improvement