Firecrawl
ExtractionTrustedLIVEby Firecrawl
Web data extraction API that turns any site into clean, LLM-ready markdown or structured JSON via scrape, crawl, map, and search endpoints. Excellent for public pages at scale with automatic proxy and rendering management. Read-only: not suitable for authenticated portals or interactive tasks.
- Provider
- Firecrawl
- Type
- Extraction
- Added
- Apr 2024
- Interface
- Task-level
- Trust tier
- trusted
- Egress
- Vendor egress (unverified)
- Evidence
- minimal
- Max session
- 30 min
- Regions
- US, EU
- Pricing
- scrape $0.80/1K pagesstructured extract +$1.50/1K pages
- Compliance
- ZDRSOC 2HIPAAPCI-DSS ROC
0.3%
Traffic share
10.5%
Success
0s
Median duration
$0.001/task
Avg $/task
—
p95 first action
Success rate over time
Traffic share over time
Pricing
| Model | Native price | Normalized $/run | Notes |
|---|---|---|---|
| per 1k steps | $0.8/1K pages crawled | $0.00 | — |
| scrape | $0.80/1K pages | — | — |
| structured extract | +$1.50/1K pages | — | — |
Capability matrix
Capabilities for this runner — extra/gap badges compare against the most common capability set for Extraction runners in the catalog.
Login flows
MFA/2FA interactions
CAPTCHA handling
File download
File upload
Form filling
Structured extraction
Vision-based
DOM-based
Stealth/anti-bot
Residential proxies
Persistent sessions
Parallel sessions
Human-in-the-loop
Full evidence
Storage capture
Code sample
Pin this runner via routing: "firecrawl"
curl -X POST "$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": "firecrawl"
}'