Skip to main content

Blazee makes it easy to deploy Machine Learning models on the cloud and turn them into an awesome prediction API.

Project description

Python Library for Blazee


Blazee is the easiest and fastest way to turn your Machine Learning models and pipelines into a production ready prediction API.

It allows you to deploy trained models straight from a Jupyter Notebook or any other model training environment, and access them live from anywhere using the Blazee HTTP API.

This library can also be used

Supported Frameworks

At the moment, we support the following frameworks:

  • Scikit Learn (Supervised learning models and pipeline)
  • Keras
  • PyTorch
  • XGBoost
  • LightGBM

Coming soon:

  • H2O
  • XGBoost
  • LightGBM
  • Tensorflow


Install from pip

pip install blazee

Sign up and get an API Key from


# Train your model like you usually do
>>> from sklearn.linear_model import LogisticRegressionCV
>>> clf = LogisticRegressionCV()
>>> ...
>>> clf.train(X)

# Deploy your model on Blazee
# Get your API Key on
>>> from blazee import Blazee
>>> bz = Blazee(YOUR_API_KEY)
>>> model = bz.deploy_model(clf)
Uploading model to Blazee...
Successfully deployed model bdea76f4-fa0f-4ef1-8bc5-f36978a4488e
Deploying model... This will take a few moments

# Predict a single sample
>>> pred = model.predict(X[0])
>>> pred.prediction
>>> pred.probas
{0: 0.08, 1:0.91, 2: 0.01}

# Or predict a batch
>>> preds = model.batch_predict(X)

# Deploy another version of the model
>>> clf2 = SGDClassifier()
>>> ...
>>> clf2.train(X)
>>> model.update(clf2)


Contact us at or open a Github Issue for any question or bug report.

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

blazee-0.1.5.tar.gz (12.4 kB view hashes)

Uploaded source

Built Distribution

blazee-0.1.5-py3-none-any.whl (28.3 kB view hashes)

Uploaded py3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page