# Deployment

> Deployment - Use DataRobot MLOps to deploy DataRobot models, as well as custom and external models
> written in languages like Python and R, onto runtime environments.

This Markdown file sits beside the HTML page at the same path (with a `.md` suffix). It summarizes the topic and lists links for tools and LLM context.

Companion generated at `2026-04-24T16:03:56.562772+00:00` (UTC).

## Primary page

- [Deployment](https://docs.datarobot.com/en/docs/classic-ui/mlops/deployment/index.html): Full documentation for this topic (HTML).

## Sections on this page

- [Feature considerations](https://docs.datarobot.com/en/docs/classic-ui/mlops/deployment/index.html#feature-considerations): In-page section heading.
- [Time series deployments](https://docs.datarobot.com/en/docs/classic-ui/mlops/deployment/index.html#time-series-deployments): In-page section heading.
- [Multiclass deployments](https://docs.datarobot.com/en/docs/classic-ui/mlops/deployment/index.html#multiclass-deployments): In-page section heading.
- [Challengers](https://docs.datarobot.com/en/docs/classic-ui/mlops/deployment/index.html#challengers): In-page section heading.
- [Prediction results cleanup](https://docs.datarobot.com/en/docs/classic-ui/mlops/deployment/index.html#prediction-results-cleanup): In-page section heading.
- [Managed AI Platform](https://docs.datarobot.com/en/docs/classic-ui/mlops/deployment/index.html#managed-ai-platform): In-page section heading.

## Related documentation

- [Classic UI documentation](https://docs.datarobot.com/en/docs/classic-ui/index.html): Linked from this page.
- [MLOps](https://docs.datarobot.com/en/docs/classic-ui/mlops/index.html): Linked from this page.
- [monitor](https://docs.datarobot.com/en/docs/classic-ui/mlops/monitor/index.html): Linked from this page.
- [manage](https://docs.datarobot.com/en/docs/classic-ui/mlops/manage-mlops/index.html): Linked from this page.
- [custom model deployment](https://docs.datarobot.com/en/docs/classic-ui/mlops/deployment/custom-models/index.html#feature-considerations): Linked from this page.
- [Deployment workflows](https://docs.datarobot.com/en/docs/classic-ui/mlops/deployment/deploy-workflows/index.html): Linked from this page.
- [Register models](https://docs.datarobot.com/en/docs/classic-ui/mlops/deployment/registry/index.html): Linked from this page.
- [Prepare for external model deployment](https://docs.datarobot.com/en/docs/classic-ui/mlops/deployment/ext-model-prep/index.html): Linked from this page.
- [Manage prediction environments](https://docs.datarobot.com/en/docs/classic-ui/mlops/deployment/prediction-env/index.html): Linked from this page.
- [Deploy models](https://docs.datarobot.com/en/docs/classic-ui/mlops/deployment/deploy-methods/index.html): Linked from this page.
- [MLOps agents](https://docs.datarobot.com/en/docs/classic-ui/mlops/deployment/mlops-agent/index.html): Linked from this page.
- [file size requirements](https://docs.datarobot.com/en/docs/reference/data-ref/file-types.html): Linked from this page.
- [Make Predictions](https://docs.datarobot.com/en/docs/classic-ui/modeling/analyze-models/predictions/predict.html): Linked from this page.
- [external deployment](https://docs.datarobot.com/en/docs/classic-ui/mlops/deployment/deploy-methods/deploy-external-model.html): Linked from this page.
- [Prediction API](https://docs.datarobot.com/en/docs/api/reference/predapi/legacy-predapi/dr-predapi.html): Linked from this page.
- [batch predictions](https://docs.datarobot.com/en/docs/api/reference/batch-prediction-api/batch-pred-ts.html): Linked from this page.
- [Enable cross-series feature generation](https://docs.datarobot.com/en/docs/reference/pred-ai-ref/ts-reference/ts-adv-opt.html#enable-cross-series-feature-generation): Linked from this page.
- [integrated enterprise databases](https://docs.datarobot.com/en/docs/classic-ui/predictions/batch/batch-dep/batch-pred-jobs.html): Linked from this page.
- [deployment approval workflow](https://docs.datarobot.com/en/docs/classic-ui/mlops/governance/dep-admin.html): Linked from this page.
- [deployment predictions](https://docs.datarobot.com/en/docs/classic-ui/predictions/batch/batch-dep/index.html): Linked from this page.
- [batch prediction limits](https://docs.datarobot.com/en/docs/api/reference/batch-prediction-api/index.html#limits): Linked from this page.
- [Challengers](https://docs.datarobot.com/en/docs/api/dev-learning/python/mlops/challengers.html): Linked from this page.
- [Feature Discovery](https://docs.datarobot.com/en/docs/classic-ui/data/transform-data/feature-discovery/fd-overview.html): Linked from this page.
- [Unstructured custom inference](https://docs.datarobot.com/en/docs/api/code-first-tools/drum/unstructured-custom-models.html): Linked from this page.
- [organization](https://docs.datarobot.com/en/docs/platform/admin/admin-overview.html#what-are-organizations): Linked from this page.
- [owners](https://docs.datarobot.com/en/docs/reference/misc-ref/roles-permissions.html#deployment-roles): Linked from this page.
- [Data drift analysis](https://docs.datarobot.com/en/docs/classic-ui/mlops/monitor/data-drift.html): Linked from this page.

## Documentation content

# Deployment

With MLOps, the goal is to make model deployment easy. Regardless of your role—a business analyst, data scientist, data engineer, or member of an Operations team— you can easily create a deployment in MLOps. Deploy models built in DataRobot and those written in various programming languages like Python and R.

The following sections describe how to deploy models to a production environment of your choice and use MLOps to [monitor](https://docs.datarobot.com/en/docs/classic-ui/mlops/monitor/index.html) and [manage](https://docs.datarobot.com/en/docs/classic-ui/mlops/manage-mlops/index.html) those models.

See the associated [deployment](https://docs.datarobot.com/en/docs/classic-ui/mlops/deployment/index.html#feature-considerations) and [custom model deployment](https://docs.datarobot.com/en/docs/classic-ui/mlops/deployment/custom-models/index.html#feature-considerations) considerations for additional information.

| Topic | Describes |
| --- | --- |
| Deployment workflows | How to deploy and monitor DataRobot AutoML models, custom inference models, and external models in various prediction environments. |
| Register models | How to register DataRobot AutoML models, custom inference models, and external models in the Model Registry. |
| Prepare custom models for deployment | How to create, test, and prepare custom inference models for deployment. |
| Prepare for external model deployment | How to create and manage external models and prediction environments in preparation for deployment. |
| Manage prediction environments | How to view DataRobot prediction environments and create, edit, delete, or share external prediction environments. |
| Deploy models | How to deploy DataRobot models, custom inference models, and external models to DataRobot MLOps. |
| MLOps agents | How to configure the monitoring and management agent for external models. |

## Feature considerations

When curating a prediction request/response dataset from an external source:

- Include the 25 most important features.
- Follow the CSVfile size requirements.
- For classification projects, classes must have a value of 0 or 1, or be text strings.

Additionally, note that:

- Self-Managed AI Platform only: By default, the 25 most important features and the target are tracked for data drift.
- For real-time, deployment predictions, the maximum payload size is 50MB for both Dedicated and Serverless prediction environments.
- TheMake Predictionstab is not available for external deployments.
- DataRobot deployments only track predictions made against dedicated prediction servers bydeployment_id.
- The first 1,000,000 predictions per deployment per hour are tracked for data drift analysis and computed for accuracy. Further predictions within an hour where this limit has been reached are not processed for either metric. However, there is no limit on predictions in general.
- If you score larger datasets (up to 5GB), there will be a longer wait time for the predictions to become available, as multiple prediction jobs must be run. If you choose to navigate away from the predictions interface, the jobs will continue to run.
- After making prediction requests, it can take 30 seconds or so for data drift and accuracy metrics to update. Note that the speed at which the metrics update depends on the model type (e.g., time series), the deployment configuration (e.g., segment attributes, number of forecast distances), and system stability.
- DataRobot recommends that you do not submit multiple prediction rows that use the same association ID—an association ID is auniqueidentifier for a prediction row. If multiple prediction rows are submitted, only the latest prediction uses the associated actual value. All prior prediction rows are, in effect, unpaired from that actual value. Additionally,allpredictions made are included in data drift statistics, even the unpaired prediction rows.
- If you want to write back your predictions to a cloud location or database, you must use thePrediction API.

### Time series deployments

- To make predictions with a time series deployment, the amount of history needed depends on the model used:
- ARIMA family and non-ARIMA cross-series models do not supportbatch predictions.
- Classic only: The ability to create a job definition for all ARIMA and non-ARIMA cross-series models is disabled whenEnable cross-series feature generationis enabled.
- All other time series models support batch predictions. For multiseries, input data must be sorted by series ID and timestamp.
- There is no data limit for time series batch predictions on supported models except that a single series cannot exceed 50MB.
- When scoring regression time series models usingintegrated enterprise databases, you may receive a warning that the target database is expected to contain the following column, which was not found:DEPLOYMENT_APPROVAL_STATUS. The column, which is optional, records whether the deployed model has been approved by an administrator. If your organization has configured adeployment approval workflow, you can: After taking either of the above actions, run the prediction job again, and the approval status appears in the prediction results. If you are not recording approval status, ignore the message, and the prediction job continues.
- To ensure DataRobot can process your time series data fordeployment predictions, configure the dataset to meet the following requirements: For dataset examples, see therequirements for the scoring dataset.

### Multiclass deployments

- Multiclass deployments of up to 100 classes support monitoring for target, accuracy, and data drift.
- Multiclass deployments of up to 100 classes support retraining.
- Multiclass deployments created before Self-Managed AI Platform version 7.0 with feature drift enabled don't have historical data for feature drift of the target; only new data is tracked.
- DataRobot uses holdout data as a baseline for target drift. As a result, for multiclass deployments using certain datasets, rare class values could be missing in the holdout data and in the baseline for drift. In this scenario, these rare values are treated as new values.

### Challengers

- To enableChallengersand replay predictions against them, the deployed model must support target drift trackingandnot be aFeature DiscoveryorUnstructured custom inferencemodel.
- To replay predictions against Challengers, you must be in theorganizationassociated with the deployment. This restriction also applies to deploymentowners.

### Prediction results cleanup

For each deployment, DataRobot periodically performs a cleanup job to delete the deployment's predicted and actual values from its corresponding prediction results table in Postgres. DataRobot does this to keep the size of these tables reasonable while allowing you to consistently generate accuracy metrics for all deployments and schedule replays for challenger models without the danger of hitting table size limits.

The cleanup job prevents a deployment from reaching its "hard" limit for prediction results tables; when the table is full, predicted and actual values are no longer stored, and additional accuracy metrics for the deployment cannot be produced. The cleanup job triggers when a deployment reaches its "soft" limit, serving as a buffer to prevent the deployment from reaching the "hard" limit. The cleanup prioritizes deleting the oldest prediction rows already tied to a corresponding actual value. Note that the aggregated data used to power data drift and accuracy over time are unaffected.

### Managed AI Platform

Managed AI Platform users have the following hourly limitations. Each deployment is allowed:

- Data drift analysis: 1,000,000 predictions or, for each individual prediction instance, 100MB of total prediction requests. If either limit is reached, data drift analysis is halted for the remainder of the hour.
- Prediction row storage: the first 100MB of total prediction requests per deployment per each individual prediction instance. If the limit is reached, no prediction data is collected for the remainder of the hour.