The Complete Platform for Production AI

Bento Cloud is the easiest way to run BentoML in production. Save time and resources by streamlining deployment for your development and production workflows.


No vendor lock-in with open source

Copyright Β© 2022 BentoML

GalleryCommunityDocumentationTutorialContactOpen SourceSchedule a Demo

BentoML's open source standard makes it easy to migrate between cloud providers and gives you the maximum flexibility to choose how you want to run your ML services.



Our fully managed platform supercharges your BentoML experience, enabling you to deploy with a single API call or click of a button.

Ship ML to prod faster

Peak performance at a low cost

Automatic optimizations let you maximize GPU and CPU resource utilization for cost efficiency.

Only pay for what you use

Serverless autoscaling allows you to scale up when you need and down to 0 when you don'tβ€”in development or in production.

Reduce operational overhead

Maintaining ML deployments requires time and effort. By letting BentoML Cloud take care of the plumbing, you can focus on building features and developing ML models.

Enable data science agility

Continuously ship new models with advanced deployment options like online and shadow A/B testing. Model performance monitoring ensures you have full visibility.

How it works

Step 1

Create your prediction service with our popular open source framework, BentoML.

Step 2

Next, upload your service, or your "Bento", to Bento Cloud.

Step 3

Lastly, choose how you want to deploy: with the click of a button or using GitOps workflow.

"BentoML is an excellent tool for saving resources and running ML at scale in production."

Woongkyu Lee

Data and ML Engineer

BentoML supports use cases across all industries

"BentoML enables us to deliver business value quickly by allowing us to deploy ML models to our existing infrastructure and scale the model services easily."

Shihgian Lee

Senior Machine Learning Engineer

πŸ’¬ Communications

✈️ Transportation

 πŸš— Automotive

Using NLP models in text based applications provides a value add service for users

Determining an ideal price in real-time helps maximize value while providing a good user experience

Determining the best flights or travel itinerary in real-time provides a competitive advantage

🏦 Financial Services

From fraud detection to credit risk scoring, financial services require production grade ML services

πŸ›’ eCommerce

Product recommendations are a proven way to increase top line revenue

 πŸ–️ Travel

Finding the best local experiences for a traveling user is key to providing value

$ bentoml push

What is BentoML?
Learn moreLearn moreLearn moreLearn moreLearn moreLearn moreSee a Demo
DocsBlogCommunityCareersPrivacy Policy