> ## Documentation Index
> Fetch the complete documentation index at: https://docs.coreweave.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Deploy models to a sandbox

> Learn how to deploy models from the Registry to CoreWeave sandboxes.

Deploy a model from Registry to an isolated [CoreWeave sandbox environment](/products/sandboxes) for testing and iteration. Send inference requests to the deployment endpoint with tools such as curl or a Python HTTP client.

<Note>
  Deploying models from Registry to sandboxes is in private preview and currently requires GPU-enabled sandboxes. To request access, contact your account team or email [support@coreweave.com](mailto:support@coreweave.com).
</Note>

CoreWeave Sandboxes have a limited lifetime and stop when they expire. When a sandbox expires, CoreWeave releases its compute resources and its endpoint becomes unavailable. To create another sandbox, [clone](/products/registry/deploy_models#clone-a-deployment) the deployment. Cloning creates a new sandbox with a new generated endpoint URL.

Deployments are scoped to your organization and associated with the team you select. To create, clone, stop, or otherwise manage deployments, you must have a [Registry role with write access](/products/registry/configure_registry#details-about-registry-roles) in the organization. Your organization must also have access to sandboxes and GPU sandboxes, available sandbox quota, and sufficient sandbox compute.

## Deploy a model

Follow the steps below to deploy a model to a sandbox:

1. Navigate to **Registry**.
2. Select a registry.
3. Select a collection.
4. Select a model version.
5. Select the action menu (<Icon icon="ellipsis" iconType="solid" />), then select **Deploy**.
6. From the **Version** dropdown, select the model version to deploy.
7. Enter a name for the deployment for the **Deployment** name field.
8. Select **Next**.
9. Select the team to associate with the deployment.
10. Select a [compute resource](/products/registry/deploy_models#compute-resources).
11. From the **Lifetime** dropdown, select how long the sandbox can run.
12. Configure the **Serving engine**. The default and currently supported engine is `vLLM`.
13. Select **Next**.
14. Review the deployment details, then select **Deploy**.

## Compute resources

The compute resource determines the CPU, memory, and GPU resources allocated to the sandbox.

| Type | Description |
| - | - |
| CPU (vCPU) | The number of virtual CPUs allocated to the sandbox. |
| Memory (GiB) | The amount of system memory allocated to the sandbox. |
| GPU | The number of GPUs allocated to the sandbox. |

<Note>
  GPU sandboxes must be enabled for your organization. Until GPUs are enabled, a request that includes a GPU fails with `CWSANDBOX_GPU_NOT_ALLOWED` and the message `this organization is not entitled to create GPU sandboxes`.
</Note>

## Sandbox states

A sandbox can have one of the following states:

| State | Description |
| - | - |
| Starting | CoreWeave is creating the sandbox and deploying the model. |
| Running | The sandbox is running and available for use. |
| Stopping | CoreWeave is stopping the sandbox. |
| Stopped | A user stopped the sandbox. Its endpoint is no longer available. |
| Expired | The sandbox reached its expiration time. Its endpoint is no longer available. |
| Failed | An error prevented the deployment from starting. |

## View a deployment

View the status, expiration time, configuration, and other details for a deployed sandbox.

1. Navigate to **Registry**.
2. Select a registry.
3. Select a collection.
4. Select a model version.
5. Select the **Deployments** tab.
6. Open the deployment details by doing one of the following:
   * Select the name of the deployed sandbox.
   * Select the action menu (<Icon icon="ellipsis" iconType="solid" />) and choose **View deployment details**.

### Deployment overview

The deployment overview includes the following information:

* **Status**: The current [state](/products/registry/deploy_models#sandbox-states) of the sandbox.
* **Created by**: The user who created the deployment.
* **Created at**: When the deployment was created.

### Sandbox configuration

The sandbox configuration includes the following information:

* **Instance name**: The name of the sandbox instance.
* **Serving engine**: The engine that serves the model.
* **Team**: The team that created the sandbox.
* **Compute resources**: CPU, memory, and GPU resources allocated to the sandbox.
* **Expires in**: The remaining time before the sandbox expires.
* **Endpoint address**: The address used to send requests to the deployed sandbox.
* **curl example**: An example request to the deployment endpoint using `curl`.

## Access a deployed model

Send requests to a deployed model by using the endpoint address in the sandbox configuration. The endpoint remains available until the sandbox expires or you stop the deployment.

<Warning>
  Sandbox endpoints are publicly accessible and don't support Forge API key authentication. Anyone with the endpoint URL can send requests to the deployed model. Don't use a sandbox endpoint for models or data that require access controls.
</Warning>

### Find the endpoint address

You can find the endpoint address for your deployed sandbox in the sandbox configuration section of the deployment overview.

1. Open the [deployment details](/products/registry/deploy_models#view-a-deployment).
2. In **Sandbox configuration**, find **Endpoint address**.

### Test the deployment

Send a chat completion request to verify that the deployment can serve inference requests.

<Tabs>
  <Tab title="Python">
    Copy and paste the following Python code to test your deployed sandbox. Set `base_url` to the endpoint address of your deployment and install `httpx` if you haven't already done so by running `pip install httpx`.

    ```python theme={"system"}
    import httpx

    base_url = "sandbox-url"

    response = httpx.post(
        f"{base_url}/v1/chat/completions",
        headers={
            "Content-Type": "application/json",
        },
        json={
            "model": "local",
            "messages": [
                {
                    "role": "user",
                    "content": "Reply with OK."
                },
            ],
            "temperature": 0,
            "max_tokens": 5,
        },
        timeout=60,
    )

    response.raise_for_status()
    print(response.json()["choices"][0]["message"]["content"])
    ```
  </Tab>

  <Tab title="curl">
    Copy and paste the following curl command to send a test request to your deployed sandbox. Replace `sandbox-url` with the endpoint address of your deployment:

    ```bash theme={"system"}
    curl --fail-with-body \
      "sandbox-url/v1/chat/completions" \
      --header "Content-Type: application/json" \
      --data '{
        "model": "local",
        "messages": [
          {
            "role": "user",
            "content": "Reply with OK."
          }
        ],
        "temperature": 0,
        "max_tokens": 5
      }'
    ```
  </Tab>
</Tabs>

## Clone a deployment

Clone a deployment to create a new sandbox with its own generated endpoint URL. By default, the cloned deployment uses the original deployment name with `-clone` appended. You can change this name before confirming the deployment.

Deployment names must be unique among deployments that are starting or running. You can reuse a name after the existing deployment stops or expires.

To clone a deployment, follow these steps:

1. Navigate to the Registry.
2. Select a registry.
3. Select a collection.
4. Select a model version.
5. Select the **Deployments** tab.
6. Select the **action** (<Icon icon="ellipsis" iconType="solid" />) menu, then select **Clone deployment**.
7. Review or update the deployment settings, then confirm the deployment.

## Stop a deployment

Stop a running deployment. You can't restart a stopped deployment, and its endpoint becomes unavailable. To serve the model again, create a new deployment.

To stop a running sandbox deployment, follow these steps:

1. Navigate to **Registry**.
2. Select a registry.
3. Select a collection.
4. Select a model version.
5. Select the **Deployments** tab.
6. Select a deployment.
7. Select the action menu (<Icon icon="ellipsis" iconType="solid" />), then select **Stop deployment**.

## Billing and usage

Deploying a model to a sandbox consumes CoreWeave sandbox compute. Model workflows can also incur product-specific usage when they use other W\&B services, such as Weave, Inference, or Training.

Organization and billing admins can review plan details, monitor usage, configure usage and spending alerts, manage payment methods, and access invoices from [Billing settings](/products/wandb/platform/app/settings-page/billing-settings).

If your account has insufficient sandbox compute, you might need to purchase additional usage, upgrade your plan, or contact CoreWeave support at [support@coreweave.com](mailto:support@coreweave.com).


## Related topics

- [Train and deploy your first model](/model-distillation/get-started/first-model.md)