---
title: Register DataRobot models
description: Add a DataRobot model to the NextGen Registry or register a model from a Workbench experiment. 
section_name: NextGen Registry
maturity: open-public-preview

---

# Register DataRobot models {: #register-datarobot-models }

After you create an [experiment](wb-experiment/index) and train models, you can register one or more models from Workbench or directly in the Registry. If a registered model already exists to solve a specific business problem, you can add new models solving the same problem as registered model versions, providing a model management experience organized by problem type.

## Register a model from Workbench {: #register-a-model-from-workbench }

To register a model from a Workbench experiment:

1. In a **Workbench** experiment, select the model from the **Models** list and then click **Model actions** > :fontawesome-solid-trophy: **Register model**:

    ![](images/nxt-reg-model-from-wb.png)

2. In the **Register a model** panel, under **Configure the model**, select one of the following:

    * **Add a version to an existing registered model**: Increment the version number and add a new version to the selected registered model.
    
    * **Create a new registered model**: Create a registered model and the first version (**V1**).
    
    Then, configure the following fields:

    ![](images/nxt-reg-model-from-wb-fields.png)

    | Field | Description |
    |-------|-------------|
    | Registered model name / Registered model | Do one of the following:<ul><li>**Registered model name:** _When registering a new model_, enter a unique and descriptive name for the new registered model. If you choose a name that exists anywhere within your organization, a warning appears.</li><li>**Registered model:** _When saving as a version of an existing model_, select the existing registered model you want to add a new version to.</li></ul> |
    | Registered version name  | Automatically populated with the model name, date, and time. Change or modify the name as necessary.
    | Registered model version | Assigned automatically. This displays the expected version number of the version (e.g., V1, V2, V3) you create. This is always **V1** when you select **Register as a new model**. |
    | Prediction threshold | _For binary classification models_. Enter the value a prediction score must exceed to be assigned to the positive class. The default value is `0.5`. |

    If necessary, you can configure the following **Optional settings**:

    | Field | Description |
    |-------|-------------|
    | Registered version description | Enter a description of the business problem this model package solves, or, more generally, describe the model represented by this version. |
    | Tags | Click **+ Add tag** and enter a **Key** and a **Value** for each key-value pair you want to tag the model _version_ with. Tags added when registering a new model are applied to **V1**. |

    !!! note
        If you click **Close** on this page to return to Workbench, you lose the configuration progress on this page.

3. Click **Register model**.

    The model version opens on the **Registry > Directory** page with a **Building** status. You can [deploy the model](nxt-deploy-models) at any time.

## Register a model from the Registry {: #register-a-model-from-the-registry }

To register a model from the Registry:

1. In the **Registry**, on the **Model directory** tab, click **+ Register model** (or the <span style="color:#297cb9">:material-plus-box:</span> button when the registered model or version info panel is open):

    ![](images/nxt-reg-model-add-new.png)

    The **Register a model** panel opens to the **External model** tab.

2. Click the **DataRobot model** tab and then, under **Configure the model**, select one of the following options:

    * **Add a version to an existing registered model**: Increment the version number and add a new version to the selected registered model.
    
    * **Create a new registered model**: Create a registered model and the first version (**V1**).

    Then, configure the following fields:

    ![](images/nxt-reg-model-configure.png)

    | Field | Description |
    |-------|-------------|
    | Use Case | Select the Use Case in Workbench containing the model you want to register. |
    | Experiment | Select the experiment in Workbench containing the model you want to register. |
    | DataRobot Model | Select the model you want to register.|
    | Registered model name / Registered model | Do one of the following:<ul><li>**Registered model name:** _When registering a new model_, enter a unique and descriptive name for the new registered model. If you choose a name that exists anywhere within your organization, a warning appears.</li><li>**Registered model:** _When saving as a version of an existing model_, select the existing registered model you want to add a new version to.</li></ul> |
    | Registered version name  | Automatically populated with the model name, date, and time. Change or modify the name as necessary.
    | Registered model version | Assigned automatically. This displays the expected version number of the version (e.g., V1, V2, V3) you create. This is always **V1** when you select **Register as a new model**. |
    | Prediction threshold | _For binary classification models_. Enter the value a prediction score must exceed to be assigned to the positive class. The default value is `0.5`. |
    | **Optional settings**  | :~~: | :~~: |
    | Registered version description | Enter a description of the business problem this model package solves, or, more generally, describe the model represented by this version. |
    | Tags | Click **+ Add tag** and enter a **Key** and a **Value** for each key-value pair you want to tag the model _version_ with. Tags added when registering a new model are applied to **V1**. |

    !!! note
        If you click **Cancel** on this page to return to the **Registry**, you lose the configuration progress on this page.

3. Click **Register Model**.

    The model version opens on the **Registry > Directory** page with a **Building** status. You can [deploy the model](nxt-deploy-models) at any time.
