1from sklearn.linear_model import LinearRegression
2from slashml import ModelDeployment
3# train the model
4lm = LinearRegression()
5data = [[1], [2], [3]]
6lm.fit(data, [2, 4, 6])
7# initialize the client
8client = ModelDeployment(api_key='YOUR_API_KEY')
9# deploy the model
10resp = client.deploy_model(lm, 'model')
11# request a prediction on the deployed model
12prediction = client.predict(model_version_id=resp.id, model_input=[[512]])
13print(prediction) # [1024.0]
Why Use SlashML
SlashML works with your existing Git pipeline and Cloud Providers
Git-Native
Git-Native ML model development. Enable GitFlow and other software engineering best practices.
Automatic Framework Detection
Automatically detect ML framework, Python requirements, and data schema.
Seamless Integration
Seamlessly integrating to your stack thanks to Unix philosophy: one tool solves one problem very well.
Pay as you go
Unlimited users and pay only for what you use
Community Plan
FREE
Startup Plan
$0.0005/ CPU compute minutes
$0.01/ GPU compute minutes
Enterprise Plan
CUSTOM
Ready to see how SlashML can help you deploy ML into production?