Check out the newest way to compare different models for a task/agent harness: AutoEvals
Deploying

Deploy

Deploy a Model

Go from a catalog or registered model to a live endpoint in a few clicks.

You can deploy open-source catalog models with weights available, and Hugging Face models you registered as custom models.

Deployments are created within a project, and access is scoped to that project — sibling projects in the same team cannot call them. When you create a deployment, you give it a name — the model path becomes your team/org slug followed by that name (e.g. acme-corp/my-model).

Starting a deployment

There are a few ways to get started:

  • From the Dedicated page — click Create Deployment
  • From the Models page — open the model's detail page and click deploy

Both paths lead to the same flow.

The flow

Name the deployment

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

Deploy

Select your instance type and count, then click deploy.

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.

On this page