Skip to content
Product
Concrete AI
Dedicated Inference
Service Boundaries
Availability

Availability

GPU availability varies by zone and GPU type. See GPU availability by zone for the current GPU-by-zone matrix.

ZoneCountryCityAvailability
at-vie-1AustriaVienna
at-vie-2AustriaVienna
bg-sof-1BulgariaSofia
ch-dk-2SwitzerlandZurich
ch-gva-2SwitzerlandGeneva
de-fra-1GermanyFrankfurt
de-muc-1GermanyMünich
hr-zag-1CroatiaZagreb

Checking for GPU capacity and authorizations

On top of the above:

  • You need to sign the GPU End User Certificate to be authorized to deploy models on RTX Pro 6000 GPUs
  • Dedicated Inference may be capacity-constrained on certain offerings

You can use the exo dedicated-inference deployment instance-type single command which allows you to know what GPU you may deploy in any given zone:

┼───────────────┼────────────┼──────────┼
│    FAMILY     │ AUTHORIZED │   ZONE   │
┼───────────────┼────────────┼──────────┼
│ gpu3080ti     │ true       │ at-vie-2 │
│ gpua5000      │ true       │ at-vie-2 │
│ gpurtx6000pro │ false      │ ch-dk-2  │
│ gpu3          │ true       │ de-fra-1 │
│ gpurtx6000pro │ true       │ de-fra-1 │
│ gpurtx6000pro │ true       │ hr-zag-1 │
┼───────────────┼────────────┼──────────┼
Last updated on