Seldon Deploy

Seldon Deploy

Productionise machine learning at scale with peak efficiency, minimal risk and the shortest time-to-value.


Seldon Deploy reduces the time to production by providing production grade inference servers optimized for popular ML framework or custom language wrappers to fit your use cases.

Serve your models how you want with advanced deployment patterns: inference pipelines, multi-armed bandits, A/B tests, shadows and canaries.


Add advanced observability & monitoring to your running deployments with built-in dashboards for all the personas you care about.

Integration with Seldon Alibi Detect provides novel drift and outlier detection capabilities to allow you to alert and take action on production data issues in real time.

Track relevant data science metrics-such as accuracy, precision, recall-in real time to ensure robust performance of your deployments.


Drive deeper insights into model behaviour with productised Explainable Artificial Intelligence (XAI) workflows. 

Generate explanations across a range of data modalities including tabular, text, and imagery leveraging state-of-the-art machine learning explainability techniques through our Alibi Explain framework.


Build repeatable deployment and monitoring pipelines with fully featured enterprise APIs and Python SDK

Manage existing machine learning models from across your enterprise through a single pane of glass.

Democratize machine learning deployment and monitoring across your organization

Seldon by numbers

0 m+
Models in production
0 K
monthly active open-source nodes
0 %
productivity gains in deploying models




Seldon Deploy allows you to deploy models in your favourite machine learning framework.



Add holistic monitoring to your running deployments with built-in dashboards for all the personas you care about.

Regulatory Compliance

Regulatory Compliance

Meet your compliance and regulatory needs with a range of explainability methods to choose from.

Model Catalogue

Model Catalogue

Use our centralized model catalog to connect your models to the data and training runs which generated them.

Model Confidence

Model Confidence

Model explainers mean you can understand and adjust what features are influencing the model and anomaly detection can flag drifts in data.

Stack Stability

Stack Stability

Backwards compatibility, rolling updates and full SLA alongside maintained integrations with frameworks and clouds means a seamless install and reliable infrastructure.

Watch a quick demo

Take a quick tour with Tom Farrand, our Head of Solutions Engineering



Plus many more


What our users say

Tom Clay_Covea CS Video_no border_without name

Seldon Deploy has enabled us to add explainers alongside 90% of our models. Now we really know our models work the way they were intended to.

Tom Clay

Chief Data Scientist, Covea

Loved by

See it for yourself

Deploy, monitor and explain your models today.


Open Source

Seldon Technologies Limited, registered in England and Wales with company number 09188032

Registered Address:
2 Underwood Row, London, N1 7LQ
United Kingdom

© 2022 Seldon Technologies. All Rights Reserved.