---
id: datarobot-predict
version: "1.13.5"
license: Apache-2.0
license_treatment: permissive
maintenance: aging
---

# datarobot-predict — DataRobot Prediction Library

License: permissive · Maintenance: aging · Downloads: 147.2K/mo

## What it is and what it does

DataRobot Prediction Library is a Python wrapper that standardizes how you call predictions across different DataRobot prediction methods. Instead of learning multiple APIs for different backends, you get one common interface that lets you swap implementations without changing your calling code. It sits on top of the datarobot package and related dependencies like pandas, requests, and py4j.

The library is intended for teams already using DataRobot who want to simplify their inference code. It abstracts the complexity of multiple prediction backends into a single entry point. The package is aging (last release 233 days ago), so while it remains functional, updates and bug fixes may come slowly.

Use it for:

- Standardize prediction calls across multiple DataRobot model types in a single application.
- Swap out prediction backends without rewriting inference code.
- Build a prediction service layer that abstracts DataRobot implementation details from application logic.
- Integrate DataRobot predictions into a larger ML pipeline with a consistent interface.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Provides a unified Python interface for making predictions using DataRobot's prediction methods, abstracting away implementation details to simplify model inference.

Yes, if you are already committed to DataRobot and want to simplify prediction code with a unified interface. The permissive license, low install friction, and lack of known vulnerabilities make it safe to use. However, the aging maintenance status means you should verify that the library supports your specific prediction methods and be prepared for slower issue resolution if problems arise.

## Install

pip install datarobot-predict
uv add datarobot-predict
poetry add datarobot-predict

## Installing datarobot-predict

Before you install: Low install friction with a pure-Python wheel. Maintenance status is aging (233 days since last release), so expect slower response to issues, though the package remains functional for its core use case.

License in practice: Apache-2.0 is permissive; you can use this library in commercial and proprietary projects with minimal restrictions, provided you include a copy of the license.

Quickstart:

pip install datarobot-predict

import datarobot_predict
# Use the library's prediction interface with your DataRobot models

Requires Python 3.8 or later; also depends on datarobot package and its transitive dependencies (pandas, requests, py4j, etc.).

Verify before relying:

- Whether the library works with all DataRobot model types or only a subset of prediction methods.
- Whether py4j dependency is required for all use cases or only for specific prediction backends.
- Current state of the official documentation and whether it covers all supported prediction methods.

## Package facts

- License: Apache-2.0 (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: aging
- Downloads: 147.2K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

datarobot prediction interface, unified prediction library, datarobot model inference, prediction abstraction layer, datarobot predictions python, common prediction interface, swap prediction backends, datarobot-integration, prediction-abstraction

[View on SkillFed](https://skillfed.io/packages/datarobot-predict) · [View on PyPI](https://pypi.org/project/datarobot-predict/)