AIAkamaiAI Orchestrator
0 regions connecting…
AMER EMEA APJ ANZ / CPU warm route cold route

Send a test request

Leave session id blank for a one-off request. Reuse the same session id across two sends to see the second one pick up KV cache affinity in the Recent Routes table below.

Datacenters

Recent Routes

SourceDestinationModelStatusDistanceWhy
No requests yet — send one above, or let real traffic arrive through the AI Router.

Models across the fleet

ModelTypeAvailable onWarm on

How routing decisions are made

MODEL AFFINITY

Stay where the model is already warm

If a model is already loaded somewhere in the fleet, new requests for it are biased toward that region instead of triggering a redundant cold load elsewhere -- better latency, less duplicate GPU memory spent on the same weights.

GEO + SATURATION

Nearest capable node, unless it's busy

Distance to the client is weighed against each node's current load. A node at capacity is excluded entirely, so traffic gracefully overflows to the next-best region instead of queuing.

COST TIER

Don't use the big GPU for a small job

Every node advertises a cost tier (premium GPU, standard GPU, or CPU). When a model is warm on both an expensive and a cheap node, the cheap one wins unless it's saturated or too far away to make sense.

KV-CACHE / SESSION

Conversations stick to their node

Each chat session carries an id. The node that served the last turn keeps serving it -- losing that would mean reprocessing the whole conversation, not just a cold model load, so this bonus outweighs generic model affinity.