Machine Learning serving engine

Easily deploy and industrialize your Machine Learning models with an efficient and scalable platform

Going from development to production with Machine Learning has never been so easy yet powerful.

Bring your ML models made from various tools and language such as TensorFlow, PMML or ONNX, and deploy them in production effortless.

We will provide in few minutes an API endpoint, Swagger and infrastructure scalability !


Take a short survey and request access to the Lab


How it works


Step 1 : train your model

Train your model with your preferred tools, export in various formats, such as TensorFlow, PMML, ONNX and so on.

ml tools


Step 2 : subscribe to this free lab

Fill out the 2 minutes survey at the bottom page (it will help us to deliver the right product to you !), then in few weeks you'll receive Lab credentials and free access.


Step 3 : download the OVHcloud exporter library

OVHcloud will provide to the lab tester the required library.


Step 4 : start the CLI

As shown below, using our library you can deploy your model very simply with one command line.

Once built, your model is up and running ! the Swagger URL will be displayed in your CLI.

ovh serving


Step 5 : Done ! Access your swagger

You can now access to your swagger in order to know how to interact with your model. As the swagger is generated with your model input, you can easily generate a client library to plug it to your code.






Features and benefits



Include your model in any framework or languages, you are not bounded to the framework used to create your ML models.



Retrace your steps with integrated versioning.


Auto Scalable

Based on amount of calls you receive and metrics we gather, such as CPU, RAM consumption and latency, we will scale your infrastructure to always provide a reliable and performant service.


API Endpoint

Deployed models are available through and HTTP API Endpoint along with a Swagger tailored to your actual model inputs.


Monitoring / Healthchecks

Powered by OVHcloud Observability, monitor your models usage, load and liveness, never feel caught off guard by an unavailable serving.


Multi-backend : TensorFlow / PMML / ONNX & more to come !

You can bring Machine Learning models made with various tools, such as Tensorflow, Scikit-Learn, PMML language or ONNX hub. The platform is backend agnostic and no format/framework is out of reach and can be added to the platform to fit your needs.


High Availability

Your models will be deployed by default on multiple instances, powered by Kubernetes.


Granular security & security policies

Manage access to models and deployments using Role Based Access Policy (RBAC).


Rolling updates

Deploy your new model version without any service interruption.


Pricing and limitations

For this free lab, we limit the amount of models, scalability and call rates. Once in production, offers will be quite more flexible with Pay-As-you-Go.


ML Serving Engine - Lab plan
Price 100% Free for lab
Models 4
Automatic scaler Yes, from 1 to 3 instances
Rate limit 500 calls per second
Tools/Languages supported (more to come)

TensorFlow, Pytorch, K, PMML, ONNX



Request your free Lab access


We are currently finalizing the first lab version.

After filling the short survery below, we will send you your credentials (It may take few weeks)


Take a short survey and request access to the Lab


Trademark policies :

  • PMML brand and logo are the property of Data Mining Group
  • ONNX brand and logo are the property of ONNX Project Contributors (MIT license)


  • BETA