CDN & edge.
A global content and compute edge that caches and runs logic close to your users.
A global edge network that caches content and runs lightweight compute close to users — cutting latency for assets and APIs, and running inference at the edge where it counts.
- Category
- Networking
- Deployment
- Managed → air-gapped
- Governance
- IAM · encryption · audit
A CDN caches bytes. This edge can also run the model.
A content delivery network's job is to serve cached assets fast from near the user, and Aether's does that — hundreds of points of presence, tiered caching, origin shielding and instant tag-based purge. But the edge is also compute, and the interesting thing to run there is increasingly a model. Aether's edge runs functions and lightweight inference close to the request, so personalisation, classification and moderation happen at the edge instead of round-tripping to a region.
Edge inference, not just edge logic.
Plenty of edges run JavaScript. Few can run a model. Because Aether distils models to run at the edge with the full model in the cloud for the hard calls, you can do real-time inference where latency is visible to the user — recommend, translate, redact or score on the way through, not after a trip to the origin and back.
One network, one boundary.
The cache, the edge compute and the origin are one platform with one identity and one audit trail, and managed TLS is handled throughout. For workloads with residency constraints, edge processing keeps sensitive data local and sends only what's needed onward.
Run a moderation model at the edge, on the way through — no round trip to a region.
export default aether.edge(async (req) => {
const body = await req.json();
const verdict = await aether.edgeModel.score("moderation", body.text);
if (verdict.block) return new Response("blocked", { status: 451 });
return fetch(origin, req); // only clean traffic reaches origin
});The moderation decision happens at the edge, near the user, before the request reaches your origin. A CDN that only runs generic logic would have to call an external model — adding the very round trip the edge exists to avoid.
Three steps to running.
Cache content across hundreds of points of presence near users.
Execute functions and lightweight inference at the edge, near the request.
Tag-based purge updates the whole network in seconds.
CDN & edge, in full.
Hundreds of points of presence with smart invalidation and tiered caching.
Run functions and lightweight inference at the edge, near the request.
Collapse origin load and absorb spikes at the edge.
Instant, tag-based cache invalidation across the network.
Provision it in a few lines.
Every service is reachable from the same SDK, CLI and infrastructure-as-code — one identity, one bill, one audit trail across the whole catalog.
# Provision cdn & edge on Aether Cloud
aether networking create \
--service cdn-edge \
--name app \
--region us-1 \
--deploy managed # or vpc | on-prem | air-gappedAt a glance.
- PoPs
- Hundreds, global
- Edge compute
- Functions + light inference
- Cache
- Tiered + origin shield
- Purge
- Instant, tag-based
- TLS
- Managed at the edge
Built for real work.
Low-latency content delivery
Edge personalization and inference
Spike absorption
On one model, not stitched together.
The usual stack runs cdn & edge in one product, the model in another and the data in a third — and the seams between them are the cost. Aether Cloud runs it on the same platform that serves the model, governs your identity and deploys into your boundary, with the rest of the catalog one hop away.
No stitching a vector DB to one place, a warehouse to another and a model to a third — cdn & edge sits next to the rest of the catalog, one identity, one bill.
The provider that runs Aether runs your cdn & edge — so the data and the model never leave the same governed boundary to talk to each other.
Need a capability that isn’t here yet? The model writes and deploys it into the same boundary — the catalog is a starting point, not a ceiling.
Good to know.
A global cache and edge-compute network — that can run Aether inference at the edge, not just static logic.
Yes — run functions and lightweight models per request close to the user.
Instant, tag-based invalidation across the whole network.
Your boundary, your choice.
Pairs well with.
Isolated software-defined networks with subnets, routing and peering across regions.
Layer-4 and layer-7 load balancing with health checks, TLS termination and autoscaling backends.
Authoritative DNS with health-based routing, traffic policies and global anycast.
Private connectivity to services and tenants without traversing the public internet.
Encrypted VPN and dedicated interconnect to bridge your network to Aether Cloud.
Stateful firewalling and a web application firewall with managed and custom rule sets.
Run CDN & edge on Aether Cloud.
A global content and compute edge that caches and runs logic close to your users. Deployable managed, in your VPC, on-prem or fully air-gapped — talk to us about the configuration your workloads and your boundary require.