SITECUBE /llms.txt Validator · AI Crawler Registry · Web-to-Token Observatory

cloudflare.com

A+ (96/100) Open to Search & Training

Cloudflare: Build for the agent era

Raw HTML Tokens: ~333,631 tok
Clean Text Tokens: ~471 tok (0.1% signal)
/llms.txt Manifest: 4,294 tok (Spec Compliant)
Edge / TTFB: Cloudflare · 291 ms
AI & /llms.txt Readiness Signal-to-Noise Ratio Token Savings via /llms.txt Network TTFB TLS & HTTP Security DNS & Edge Stack
96/100 0.1% (471 / 333,631 tok) -98.7% fewer tokens 291 ms (84/100) 100/100 Cloudflare (Astro)

Web-to-Token Efficiency & Agent Ingestion Cost

~4 bytes/token UTF-8 heuristic
Ingestion Source Payload Est. Tokens Cost / 1k Reads (Flash $0.35) Cost / 1k Reads (Pro $1.25)
Raw HTML DOM (GET /) 1,303.2 KB 333,631 $116.7709 $417.0388
Stripped Readable Text 1.8 KB 471 $0.1649 $0.5888
/llms.txt Manifest 16.8 KB 4,294 $1.5029 $5.3675
HTML Signal-to-Noise Ratio: 0.1% readable text vs. 99.9% markup/script overhead.

/llms.txt Spec Linter & Agent Endpoint Probe

Status: Spec Compliant
GET /llms.txt HTTP 200 · 17,173 bytes (~4,294 tokens · 185 lines)
Spec Check: # H1 Title Pass ("Cloudflare")
Spec Check: > Summary Pass ("Cloudflare is a global cloud connectivity company operating in 335+ cities worldwide. It provides a unified platform spanning developer infrastructure (serverless compute, database")
## H2 Sections & Links 13 sections · 90 canonical markdown links
GET /llms-full.txt HTTP 200 · 169,547 bytes (~42,387 tokens)
GET /.well-known/mcp.json Active Model Context Protocol Manifest
JSON-LD Schema Entities Organization, WebSite, SearchAction, WebPage
Live Payload from https://cloudflare.com/llms.txt
# Cloudflare

> Cloudflare is a global cloud connectivity company operating in 335+ cities worldwide. It provides a unified platform spanning developer infrastructure (serverless compute, databases, AI inference, and storage), application security (WAF, DDoS mitigation, bot management, and API Shield), Zero Trust / SASE (Access, Gateway, Browser Isolation, DLP, and Email Security), and network services (CDN, DNS, load balancing, and Magic Transit). Cloudflare powers approximately 20% of Internet

AI Crawler /robots.txt Access Matrix

Open to Search & Training
User-Agent Token Purpose / Operator Effective Directive
OAI-SearchBot ChatGPT Search Citations Allow: /
PerplexityBot Perplexity Answer Citations Allow: /
ChatGPT-User Live User Agent Browsing Allow: /
Claude-SearchBot Anthropic Search Grounding Allow: /
GPTBot Foundation Model Training Allow: /
ClaudeBot Foundation Model Training Allow: /
Google-Extended Gemini Training Control Allow: /
Applebot-Extended Apple Intelligence Training Allow: /
Meta-ExternalAgent Llama Training & Indexing Allow: /
CCBot Open Dataset Training Corpus Allow: /

HTTP Response & Handshake Timing

GET https://www.cloudflare.com/
DNS Lookup 11 ms HTML Document 1303.2 KB
TCP Connect 19 ms Script Tags 22
TLS Handshake 0 ms Stylesheets 4
Time to First Byte (TTFB) 291 ms Images (with alt) 67 / 68
Total Transfer 319 ms HTTP/3 (Alt-Svc) Yes (h3)

Edge Network & Application Stack

Header & DOM Signatures
Edge / Reverse Proxy Cloudflare
Application Framework Astro
Server Header cloudflare
Mail Provider (MX) Custom MX
Telemetry Signatures GA4 / GTM
TXT Verifications Google Search Console, Stripe Verified, Atlassian, Microsoft Entra

TLS Certificate & HTTP Security Policy

Port 443 X.509
Certificate Issuer Google Trust Services (79 days remaining)
Strict-Transport-Security Present
Content-Security-Policy Present
X-Content-Type-Options Present
X-Frame-Options Present
Referrer-Policy Present
Permissions-Policy Present
SPF / DMARC Policy SPF: Yes · DMARC: Yes

Authoritative DNS & Document Head

A / AAAA / NS / Canonical
A (IPv4) 104.16.133.229, 104.16.132.229
AAAA (IPv6) 2606:4700::6810:85e5, 2606:4700::6810:84e5
NS (Nameservers) ns3.cloudflare.com, ns5.cloudflare.com, ns6.cloudflare.com, ns7.cloudflare.com, ns4.cloudflare.com
HTML Title (35c) Cloudflare: Build for the agent era
/sitemap.xml Valid XML Sitemap

Hosted /llms.txt Mirror & Status Badge

Platform Setup Guide →
1-Line <head> Tag (for Shopify, Webflow, Framer, Wix, Squarespace & WordPress):
Sitecube status for cloudflare.com
GitHub / Docs Markdown Badge:
HTML Badge:

Technical Synthesis & Agentic Ingestion Analysis: cloudflare.com

Automated Engineering Assessment

1. HTML-to-Token Efficiency & LLM Context Window Cost

An unauthenticated HTTPS GET request to https://www.cloudflare.com/ returns an initial HTML payload of 1,303.2 KB, corresponding to approximately 333,631 UTF-8 tokens when ingested raw by an AI coding agent, retrieval pipeline, or headless browser. After stripping inline <script>, <style>, <svg>, and DOM markup tags, the human-readable text footprint measures 471 tokens (1.8 KB)—yielding an HTML Signal-to-Noise Ratio of 0.1%. Because cloudflare.com publishes a valid /llms.txt manifest (measuring 4,294 tokens across 185 lines), AI retrieval agents that read /llms.txt instead of scraping the raw DOM reduce token consumption by 98.7%—cutting 1,000-read inference input costs from $417.0388 to $5.3675 at frontier model rates ($1.25/1M tokens), or $1.5029 on Gemini 4 Hydrogen ($0.35/1M).

2. Indexed Structure Inside cloudflare.com/llms.txt

Sitecube’s specification linter verified 13 H2 section headings and 90 Markdown links inside https://cloudflare.com/llms.txt under the primary heading "Cloudflare". Documented sections include: About Cloudflare</code>, <code>Developer Platform - Compute</code>, <code>Developer Platform - Storage</code>, <code>Developer Platform - AI</code>, <code>Developer Platform - Media</code>, <code>Application Security</code>, <code>Zero Trust / SASE (Cloudflare One)</code>, <code>Network & Performance. Key canonical endpoints referenced in the manifest include Workers (https://www.cloudflare.com/products/workers.md), Containers (https://www.cloudflare.com/products/containers.md), Durable Objects (https://www.cloudflare.com/products/durable-objects.md), Sandboxes (https://www.cloudflare.com/products/sandboxes.md), Workflows (https://www.cloudflare.com/products/workflows.md).

3. Edge Delivery, TLS Handshake & Security Header Assessment

Traffic for cloudflare.com resolves to 104.16.133.229 via Cloudflare running Astro, achieving a measured Time to First Byte (TTFB) of 291 ms (DNS lookup: 11 ms, TCP connect: 19 ms, TLS handshake: 0 ms). The port 443 TLS certificate is issued by Google Trust Services with 79 days remaining before expiration (valid through 2027-02-01). Outbound email authentication via SPF is present and DMARC (_dmarc.cloudflare.com) is enforced.

Comparable Hosts in Web-to-Token & /llms.txt Registry

Full Index (26 hosts) →
Host Rating /llms.txt HTML Tokens Text Tokens Signal % Crawler Posture TTFB
sitecube.com A+ 98 1,600 tok 11,832 1,132 9.6% Open to Search & Training 99 ms
cloudflare.com A+ 96 4,294 tok 333,631 471 0.1% Open to Search & Training 291 ms
trendyflash.com A+ 95 2,987 tok 12,123 1,660 13.7% Open to Search & Training 112 ms
multifactor.com A+ 94 656 tok 98,275 673 0.7% Open to Search & Training 97 ms
github.com A+ 92 7,165 tok 131,504 1,159 0.9% Open to Search & Training 35 ms
vercel.com A+ 92 1,385 tok 149,859 889 0.6% Open to Search & Training 53 ms
aiimpacted.org A+ 92 971 tok 17,598 3,568 20.3% Open to Search & Training 55 ms
tierones.io A+ 92 481 tok 3,744 693 18.5% Open to Search & Training 95 ms
cloq.com A 91 1,169 tok 2,109 690 32.7% Open to Search & Training 51 ms
supabase.com A 89 879 tok 337,513 1,905 0.6% Open to Search & Training 48 ms
dosefacts.org A 89 10,936 tok 29,008 7,291 25.1% Open to Search & Training 335 ms
postman.com A 89 5,375 tok 118,892 11,040 9.3% Open to Search & Training 947 ms