Crawl4AI

Crawl4AI

ExtractionLIVE

by Crawl4AI

The most-starred open-source LLM-friendly crawler (50K+ GitHub stars): clean markdown output, adaptive crawling, and schema-based extraction. Self-hosts with a single Docker command. Heuristic extraction avoids LLM costs wherever possible.

Provider
Crawl4AI
Type
Extraction
Added
Jun 2024
Interface
Task-level
Trust tier
restricted
Egress
Vendor egress (unverified)
Evidence
minimal
Max session
15 min
Regions
US, EU
Pricing
license free (Apache-2.0)compute operator-paid
Compliance
ZDRSOC 2HIPAAPCI-DSS ROC
0.3%
Traffic share
0.0%
Success
0s
Median duration
Free · OSS
List price
p95 first action

Success rate over time

Traffic share over time

Pricing

ModelNative priceNormalized $/runNotes
ossFree (self-hosted)$0.00
licensefree (Apache-2.0)
computeoperator-paid

Capability matrix

Capabilities for this runner — extra/gap badges compare against the most common capability set for Extraction runners in the catalog.

Login flows
MFA/2FA interactions
CAPTCHA handling
File download
File upload
Form filling
Structured extraction
Vision-based
DOM-based
Stealth/anti-botextra
Residential proxies
Persistent sessions
Parallel sessions
Human-in-the-loop
Full evidence
Storage capture

Code sample

Pin this runner via routing: "crawl4ai"

curl -X POST "$BANANA_PEEL_BASE/api/v1/responses" \
  -H "Authorization: Bearer $BANANA_PEEL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "banana-peel",
  "input": "Extract the title from https://example.com",
  "routing": "crawl4ai"
}'

Command Palette

Search for a command to run...