Skip to content
Crawl4AI Web Extractor AI Platform & Data · Crawl4AI 0.9.5 Launch on AWS

Getting started

Launch Crawl4AI, run the walkthrough, and call the API through a Session Manager tunnel.

You need: an AWS account that can subscribe, launch EC2, and start Session Manager. Install the AWS CLI and the Session Manager plugin on your workstation.

Watch on YouTube.

1. Subscribe

Open the Crawl4AI listing, choose View purchase options, review the terms, and subscribe. When the subscription is active, choose Launch your software.

2. Launch the instance

  1. Choose t3.large with at least 8 GiB of memory.
  2. Use an encrypted gp3 root volume of 32 GiB.
  3. Require IMDSv2 and attach AmazonSSMManagedInstanceCore.
  4. Leave inbound application ports closed.
  5. Choose Launch instance.

Wait until cloud-init finishes. First boot creates the TLS certificate and the API token and starts the crawler on port 8447. Do not print the token.

3. Run the walkthrough

sudo -iu ubuntu bash /opt/sushi/docs/demo.sh

4. Call the API

Forward port 8447. Trust the certificate from this instance before you call the API.

aws ssm start-session --target <instance-id> \
  --document-name AWS-StartPortForwardingSession \
  --parameters '{"portNumber":["8447"],"localPortNumber":["8447"]}'

The request shape is in /opt/sushi/docs/README.md. The listing does not paste a sample body into the usage text.

Next, see Configuration.

Last updated November 1, 2026 · Suggest an improvement