Skip to main content
When training completes, the model is automatically registered and ready to deploy. No manual promotion step.

​
The flow

1

Navigate to Deployments

Go to the Deployments page in your project.
2

Name the deployment

Give it a descriptive name so you can identify it later.
3

Deploy

Click deploy. No GPU type or size selection needed — it’s automatically determined by the recipe used during training.
4

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. The deployment gets a unique model identifier — just swap it in.