Skip to main content
A dedicated endpoint is a private GPU deployment of a model, reserved for your workspace. Unlike shared per-token inference, you get isolated, guaranteed capacity, billed per GPU-hour with per-minute granularity, only while it runs.

​
When to use dedicated

Guaranteed throughput

Reserved GPUs mean predictable latency and no contention with other tenants.

Isolation

Your traffic runs on capacity dedicated to your workspace.

Serve fine-tuned models

Deploy a model you fine-tuned and call it by its routing key.

Sustained high volume

At high, steady request rates a dedicated GPU can be more economical than per-token pricing.

​
How billing works

Dedicated endpoints are billed per GPU-hour, metered per-minute, while the endpoint is running, not per token. The rate depends on the GPU type, GPU count, and number of running replicas. Individual inference requests to the endpoint carry no per-token charge; you’ve already paid for the GPU time. The GPU price is Omnia’s own configured rate (which includes the platform’s markup). The available GPU types, regions, and flavors come from the templates endpoint, so you always deploy against combinations that actually exist.
Deploying requires enough prepaid balance to cover a minimum runway (by default one hour of GPU time). If your wallet can’t cover it, deployment is refused and the response tells you the exact shortfall to add.
A running endpoint whose wallet becomes exhausted is automatically stopped to prevent further charges. Top up the wallet and start it again when you’re ready.
See Billing for how the wallet is charged across shared, dedicated, and fine-tuning usage.

​
Autoscaling

An endpoint autoscales between the minReplicas and maxReplicas you set. It scales up under load and back down when idle, and cost scales with the number of running replicas. Set minReplicas to keep warm capacity always available, and maxReplicas to cap both throughput and spend.

​
Lifecycle

1

Deploy

Pick a base model, GPU type, count, region, and replica range. See Deploying an endpoint.
2

Use

Route to the endpoint by passing model = dedicated/<routing-key> on the normal inference API. It autoscales within the range you set.
3

Manage

Scale, disable, or delete it any time. See Managing endpoints.

​
Managing via API or dashboard

You deploy and manage dedicated endpoints from the dashboard, or programmatically against the management API at https://gateway.omnia-voice.com/v1 using the same workspace API key you use for inference. Creating, updating, and deleting endpoints are admin-gated operations. See Deploying an endpoint and Managing endpoints.
If you need a GPU count above 8 per replica, or a region that isn’t listed in the templates, the dashboard shows “contact sales”; those deployments are arranged directly.