Skip to main content
When training completes, the model is automatically registered and ready to deploy. No manual promotion step. Deployments are scoped to your team, not a specific project. When you create a deployment, you give it a name — the model path becomes your team slug followed by that name (e.g. acme-corp/my-model).

​
Starting a deployment

There are a few ways to get started:
  • From the Deployments page — click Create
  • From a completed training run — click deploy directly from the training detail page
  • From the Models page — click deploy in the row for your model
All three paths lead to the same flow.

​
The flow

1

Name the deployment

Give it a descriptive name. This becomes the second part of your model path (e.g. acme-corp/my-model).
2

Deploy

Select your instance configuration and click deploy. If you need more compute than a single GPU, you can reach out to the team directly from this page.
3

Wait for warm-up

The deployment takes a few minutes to 20–30 minutes to come online. This time is spent allocating compute and spinning up the GPU.

​
After deployment

Once the endpoint is live, you can call it using the same OpenAI-compatible API you’re already using. Just swap in your model path.