Models

Deploy, operate, and share your models from the dashboard.

The Models screen is the operational heart of the dashboard. From here you deploy models, inspect running deployments, control their lifecycle, and manage who can access them. Tabs filter by Active, All, Failed, and Terminated.

The Models screen, showing the deployment stages a model passes through.

Deployment stages

A model is only ready to use once it reaches Running. It passes through:

Queued → Provisioning → Downloading weights → Initializing → Health check → Running

The screen shows this progression live, so you can see exactly where a starting deployment is.

Deploy

Start a new deployment from a base model (any Hugging Face model) or from one of your fine-tuned models. See Deploy a model for the full flow.

Operate a deployment

Each deployment can be managed over its whole lifecycle:

Action	What it does
Stop / Resume	Release the GPU when idle; bring it back on demand
Restart	Restart the serving process without redeploying
Health	Check that the model is actually serving requests
Schedule	Start/stop automatically on a cron schedule
Auto-restart	Recover the service if it becomes unhealthy

A running deployment holds a GPU and costs money even when idle. Use stop/resume or a schedule to control spend, see Quota & billing.

Share a model

You can grant teammates access to a model by email from its detail screen. The owner can see who has access and which keys each person holds against the model, and can revoke access, which invalidates the keys tied to that grant. Models shared with you are marked in the models list and when creating a key.

Get the endpoint

A ready deployment exposes an OpenAI-compatible endpoint at /{deployment_slug}/v1/.... Attach an alias for a stable URL, and see Run inference to call it.