21 live use cases · real Workers AI · $0 egress · 330+ cities · collab room designer

One Worker in front of your site. Zero origin changes. Live in 330+ cities.

Scroll

Start here

One Worker. Every capability.

A Cloudflare Worker intercepts every request before it reaches your origin. It can run AI models, cache in R2 or KV, rewrite HTML, detect the visitor's country — all at the edge, with 0ms cold starts (V8 isolates eliminate the VM boot model), in 330+ cities. Your origin receives a completely normal request and never knows any of this happened.

CLOUDFLARE NETWORK · 330+ CITIES · 0ms COLD STARTS EXTERNAL INTERNET · fetch() ANY URL · ANY SERVICE · ANYWHERE 🤖 Workers AI env.AI.run() 🔍 Vectorize env.VECTORIZE 📦 R2 Storage env.R2.put() Workers KV env.KV.get() 🗄️ D1 Database env.DB.prepare() 🔵 Durable Objects env.DO.get(id) 👤 User Browser CLOUDFLARE Worker intercepts every request 🏠 Origin Unchanged ✓ REQUEST RESPONSE fetch(request) origin response fetch() — any URL, any service, anywhere 🌐 OpenAI / AI APIs api.openai.com 💳 Stripe / Payments api.stripe.com 🔌 Any REST API your-api.com 🗃️ Customer DB / ERP internal.corp
HTTP request
Cloudflare binding
External fetch()
Animated = live data
330+ cities in 125+ countries  ·  13,000 network peers  ·  ~50ms from 95% of the world  ·  cold start <1ms
See how Workers intercept →

HTMLRewriter · Workers AI · GLM-4.7-Flash

AI on any site.
15 minutes.

HTMLRewriter streams through your origin HTML and injects a Llama-powered chat widget — before the browser sees a single byte. No frontend PR. No backend deploy. No new infrastructure.

Your server returns the same response it always has. The Worker does the rest — in the same milliseconds the response was already travelling.

Live demo → Open STREAMVAULT →
Before → After
// Worker code
const res = await fetch(request)
return new HTMLRewriter()
  .on('body', {
    element(el) {
      el.append(chatWidget, {
        html: true
      })
    }
  })
  .transform(res)
Deploy time~15 min
AWS S3 vs Cloudflare R2
Storage $0.023/GB $0.015/GB
Egress $0.09/GB* $0.00
customMetadata Not auditable cached-at · size-bytes · origin-url
URL changes None

Cloudflare R2 · $0 egress

Kill your egress bill.
Keep your URLs.

AWS charges $0.09/GB (first 10TB tier) to send data to your users. R2 charges $0.00 — permanently, not as a promo. Same URLs, same latency from the nearest Cloudflare PoP, zero DNS changes. *AWS S3 Standard, US-East-1, first 10TB tier (Apr 2026).

Every object gets customMetadata stamped on first cache — timestamp, file size, origin URL — visible in the dashboard and verifiable via response headers.

Run the demo Try it Yourself →

21 live demos.

AI · $0 egress · semantic search · SEO · voice · video · caching · geo pricing · subtitles · collab room designer — none touched the origin.

Workers Routes
0
origin changes

How Workers Intercept

The concept every other demo here relies on: a Worker sits in front of your site via a route pattern, transforms the response, and your origin never knows it exists. ~8 lines of code, zero backend changes.

Learn more →
HTMLRewriter · Workers AI · AI Search
15 min
to deploy

AI Chatbot Injection

HTMLRewriter injects a live chatbot into any existing page, grounded in your real product catalog via AI Search — not generic LLM knowledge. Zero origin changes, one Worker route.

Learn more →
Cloudflare R2
$0
egress fees

R2 Storage — Zero Egress

Watch the AWS/GCS egress cost ticker climb in real time as images load, while R2 stays at $0.00 for the exact same traffic. Swap the storage binding, keep everything else.

Learn more →
Vectorize · Workers AI
more results

Semantic Search

"Comfortable reading chair" finds the POÄNG Armchair even though not one word matches. One embedding call + a Vectorize query — ~30 lines, no Elasticsearch cluster to run or maintain.

Learn more →
Workers AI · distilbert
$3.90
to score 1M reviews

AI Sentiment Analysis

A Worker enriches your existing reviews API with real-time sentiment scores — the backend behind it never changes. distilbert costs $0.026/M input tokens; scoring 1M reviews ≈ $3.90.

Learn more →
Edge Compute · request.cf
0ms
geo lookup latency

Local Currency at the Edge

5 lines read request.cf.country, 3 more convert the price. ฿ / Rp / S$ / RM shown to every visitor — zero geo-IP API subscription, zero added latency.

Learn more →
Workers KV
166
origin calls/hour at 10K req/h

KV Edge Caching

A ~10-line cache-aside pattern turns 10,000 origin calls/hour into 166 with a 60-second TTL. Hot reads land in 500µs–10ms from the nearest Cloudflare PoP.

Learn more →
Workers AI · Whisper · Nova-3 · WebVTT
48×
cheaper vs AWS Transcribe

Auto Subtitles

Upload a clip — Workers AI routes to the right STT model per language, runs a two-pass AI correction, and exports a timestamped .vtt. One POST request; AWS needs S3, IAM, and a batch pipeline.

Learn more →
RealtimeKit · Workers AI
1
Worker to deploy

AI Voice Agent

Speech-to-text, LLM reasoning, and text-to-speech chained in one Worker endpoint — no separate voice infrastructure to provision, reply back in under 2 seconds.

Learn more →
Cloudflare Images
98%
smaller on mobile

Image Resizing

No Worker code at all — just a URL prefix. Converts to WebP/AVIF and resizes per device automatically: 1.1 MB shrinks to 15 KB on mobile, measured live on this page.

Learn more →
Workers AI · Vectorize
15 min
per new endpoint

Build APIs at the Edge

Four AI-powered endpoints your origin has never seen — style match, assembly guide, mood discovery, watchlist planner. ~30 lines each, deployed in 15 minutes, zero backend sprint.

Learn more →
Cloudflare Stream · Adaptive Bitrate · HLS
$1
per 1K min delivered

Video Streaming

Marketing uploads a video — Stream auto-encodes every quality level, delivers adaptive bitrate from 330+ cities, and builds the player. Zero engineering tickets, $0 egress.

Learn more →
Workers AI · LLM
review completion

AI Review Assistant

A blank textarea kills review completion. Workers AI generates tone-matched tags and a full draft review in under 2 seconds — completion rate roughly triples.

Learn more →
HTMLRewriter · JSON-LD · Workers
0
backend changes

SEO — Rich Results at the Edge

Your React SPA sends Googlebot the same blank title on every URL. A Worker injects unique titles, meta descriptions, and JSON-LD via HTMLRewriter — no SSR migration required.

Learn more →
Durable Objects · WebSocket Hibernation · SQLite
$0
1,000 idle connections / month

Collaborative Room Designer

What gets scoped as a 6-month build — WebSocket server, Redis pub/sub, load balancer — is one ~400-line Durable Object class here. SQLite persists state; Hibernation makes idle connections free.

Learn more →
Workers AI · Vision · Moondream
$0.0000075
per DETR inference

Live Object Detection

Point your phone camera — Workers AI finds objects at the edge in under a second. Fixed 80-class detection for a fraction of a cent, or open-vocabulary/caption/OCR via Moondream on the same endpoint.

Learn more →
Workers AI · Vision · Llama 4 Scout
1
model, any question

Visual Q&A Assistant

Ask any question about a photo in plain English — "does this look damaged?" — with multi-turn follow-ups. One natively multimodal model, no separate vision pipeline to build.

Learn more →
Workers AI · Flux-2 Klein
10-15s
per edit or generation

AI Photo Editor

Upload a photo and describe an edit in plain English, or skip the upload and generate one from scratch. One Workers AI model, two modes, no diffusion pipeline or masking UI to build.

Learn more →
Workers AI · Moondream · One Model, Five Scenarios
<60
lines of code for all 5 scenarios

Scenario Vision Monitor

Object counting, baby distress, fall detection, exam-integrity flagging, safety flagging — five monitoring ideas, one Workers AI model, five prompts. Proves how cheaply a new AI use case can be prototyped before committing engineering budget.

Learn more →
AI Search · AutoRAG
1
call for embed + retrieve + rerank

Ask our Knowledge Base

A classic FAQ search box — but retrieval is one AI Search call, not a Vectorize index you build and own. Cites the exact source document behind every answer, and honestly says "I don't know" when nothing relevant is found.

Learn more →
Workflows · Durable Execution · D1
1 class
replaces a hand-rolled retry queue

Order Fulfillment Pipeline

A real checkout — cart, email, shipping address — running seven durable steps: validate against D1, charge, invoice, render a real PDF via Browser Rendering, sleep for the warehouse, email that PDF, notify fulfillment. Watch the payment step fail and retry with backoff live, then download the actual invoice PDF.

Learn more →

For your engineering team

Ship it on your domain today.

Two production-ready Workers — AI chatbot and R2 image cache. No ORIGIN constant to configure, no origin to touch. Deploy to any hostname, bind a bucket or an AI binding, done. Your team can have either live in under an hour.

Try it Yourself Ballpark pricing →