Seldonvs
AWS SageMaker
AWS SageMaker: Build, train, and deploy machine learning models at scale
Seldon
Kubernetes model serving whose current version is licensed under the Business Source Licence
As of 30 August 2026, Seldon is free to use. Seldon deploys models on Kubernetes as inference graphs with routing, canaries and explainability. Softwr lists it under Machine Learning. Seldon is made by Seldon Technologies, launched in 2014, available on Linux.
Overview
What Seldon does
Seldon is model serving infrastructure for Kubernetes, from Seldon Technologies in London. A deployment is described as a Kubernetes custom resource and an operator creates the pods, routing and scaling behind it, supporting multi-step inference graphs, traffic splitting, shadow deployments and canaries, with drift detection and explanation available through the companion Alibi libraries. There are two generations. Seldon Core v1 is Apache 2.0 and is in maintenance. Seldon Core v2 is a different architecture built around a scheduler, model servers and Kafka-backed pipelines, and it was relicensed under the Business Source Licence in 2024, which permits evaluation and non-production use but requires a commercial agreement to run in production. The technical distinction is the inference graph. Most serving tools put one model behind one endpoint; Seldon models a request path with several stages, a transformer, two models, a combiner, a router, deployed, versioned and scaled as one unit. Teams that need ensembles, request-time feature transformation or genuine traffic-split experiments in production adopt it for that. Commercially, though, the licence change is now the more consequential fact for anyone evaluating it, because the version that remains freely usable in production is the one that is no longer being developed. It is bought by enterprises with existing Kubernetes platform teams and serving requirements beyond a single endpoint, typically in banking, insurance and telecommunications, and it assumes an engineer who is fluent in Kubernetes rather than in modelling. The trade-off has two parts. The infrastructure cost is real, because v2 pipelines depend on Kafka, which an organisation that does not already run it acquires purely in order to serve models. And the licensing cost arrives late, because the thing evaluated free is not the thing that can be run free.
What people use it for
- Serving an ensemble or a multi-stage inference path as one versioned deployment rather than as a chain of separate services
- Running genuine production experiments where a share of live traffic goes to a candidate model and the results are compared
- Regulated environments needing explanations and drift monitoring attached to the served model rather than bolted on later
- Organisations with an established Kubernetes platform team who want serving expressed as manifests under existing deployment controls
Related searches
The honest half
Where it falls short
Concrete and checkable, so you can decide whether any of them matter to you. This is the half of a review a vendor will not write about Seldon.
- Seldon Core v2 is under the Business Source Licence rather than Apache 2.0, so production use requires a commercial agreement, and a team that evaluated it believing it was open source discovers the licence is the blocker exactly when the project is ready to ship.
- Core v1 remains Apache 2.0 but is in maintenance, so taking the free route means running software that receives no new development while the architecture it belongs to moves on without it.
- Version 2 is a different system rather than a newer release, with different custom resources, a scheduler component and a Kafka-based pipeline model, so migrating from v1 is a re-implementation of every deployment manifest rather than an upgrade.
- Kafka is a dependency for v2 pipelines, so an organisation that does not already operate it takes on a distributed log with its own storage, retention, rebalancing and failure modes purely in order to serve models.
- Everything assumes Kubernetes fluency and the failure modes are Kubernetes failure modes, custom resource version mismatches, an operator that will not reconcile, admission webhooks and resource limits terminating an inference pod mid-request, so it needs a platform engineer rather than a data scientist.
Cross-shopped
What people choose instead of Seldon
Each pairing was judged by two reviewers asking whether a buyer would genuinely weigh the two against each other. The ones that failed were deleted rather than published.
- SeldonvsGoogle Vertex AI
Google Vertex AI: Unified ML platform to build, deploy, and scale AI models
- SeldonvsAzure Machine Learning
Azure Machine Learning: Enterprise-grade machine learning service
- SeldonvsDataRobot
DataRobot: Enterprise AI platform for automated machine learning
Pricing
What Seldon costs
Taken from the vendor's own pricing page. Prices move, so check before you buy.
Seldon Core
Free
- Open source
- Kubernetes deployment
- Model serving
Seldon Deploy
Free
- Enterprise features
- GUI
- Monitoring
Capabilities
Features
Kubernetes custom resources
Deployments declared as manifests and reconciled by an operator, so serving fits existing GitOps practice
Inference graphs
Multi-step request paths with transformers, routers, combiners and several models as one deployable unit
Traffic strategies
A/B splits, canary rollouts and shadow traffic for testing a new model against live requests
Open Inference Protocol
Standard prediction interface via MLServer and compatible runtimes
Alibi Explain
Explanation methods including counterfactuals and anchors deployed alongside a model
Alibi Detect
Outlier, adversarial and drift detection on live inference traffic
Kafka-backed pipelines in v2
Inference steps connected through a log, giving asynchronous and replayable request flows
Commercial control plane
Seldon's paid products add management, governance and monitoring interfaces above the serving layer
Answered, with sources
Questions people ask
Each answer names the page it came from, so you can check it rather than take our word for it.
Is Seldon open source?
Partly, and this is the thing to check before you build on it. Core v1 is Apache 2.0 but in maintenance. Core v2 was moved to the Business Source Licence in 2024, which allows evaluation but not unlicensed production use. Verify the current licence of each component you intend to run, including MLServer and the Alibi libraries.
What is the difference between v1 and v2?
Architecture, not just version number. v2 introduces a scheduler, a different set of custom resources and Kafka-backed pipelines. Manifests, mental model and operations all change, so treat a move as a project.
Do I need Kubernetes?
Yes. It is a Kubernetes-native system and there is no meaningful deployment without a cluster and someone competent to run it.
What is MLServer?
Seldon's Python inference server implementing the Open Inference Protocol, usable inside Seldon deployments or on its own. Check its current licence alongside Core's, since the company has moved projects onto the Business Source Licence.
Do I have to run Kafka?
For v2 pipelines, yes. If you only need single models served, that dependency is a large amount of infrastructure for the benefit, and a simpler serving layer may be the better answer.
Behind it
Who makes Seldon
- Company
- Seldon Technologies
- Based in
- London, United Kingdom
Keep looking
Where to go from Seldon
- Seldon alternativesEvery product people weigh against it
- Seldon pricingPlans, floors and what the tiers exclude
- Seldon badgesWhich rules it meets, and the figure behind each
- All Machine Learning softwareThe full category
- Best Machine Learning softwareThe shortlist, and how it was cut
Best Machine Learning software for
Compare Seldon with
- AWS SageMaker
- DataRobot
- Azure Machine Learning
- Google Vertex AI
- BentoML
- Kubeflow
- Pachyderm
- MLflow
- DVC
- Weights & Biases
- Comet ML
- Dataiku
- Anaconda
- Domino Data Lab
- H2O.ai
- Hugging Face
- Kubeflow
- DVC
Other Machine Learning software
Build, train, and deploy machine learning models at scale
Free, then $0.04/hour9 researched notesMicrosoft's managed platform for training, tracking and deploying models on Azure
Free plan13 researched notesOpen source Python framework that packages models into deployable inference services
Free plan14 researched notesData versioning and container pipelines that run on your Kubernetes cluster
Free plan14 researched notesGit-style versioning for data sets and models, with the files kept in object storage
Free plan14 researched notesPlatform for tracking, comparing, and optimizing ML experiments
Free, then $19/mo13 researched notesBrowser-based platform where visual data preparation and written code share one pipeline
Free plan14 researched notesGit-style versioning for data sets and models, with the files kept in object storage
Free plan14 researched notes
Softwr does not host reviews and shows no star rating for Seldon, because a rating we did not collect is not ours to publish. What is here is the pricing and platform detail from the vendor’s own pages, limitations we could state concretely, and alternatives a reviewer confirmed people weigh against it. Tell us if any of it is wrong.
More on Seldon
Seldon alternatives
What people switch to, and what they give up
Seldon pricing
Every tier, and where the cost actually lands
Compare Seldon
Put it head to head with anything we hold
Seldon badge
Its rating, and an embed for your own site
Best Machine Learning software alternatives
Open-source MLOps platform for experiment tracking and orchestration
Open-source self-hosted, with paid hosted and enterprise tiers
LLM engineering platform for testing and evaluating AI agents in production
Tiered subscription with usage-based overage charges
Open-source AI orchestration framework for LLM applications
Open-source with optional paid enterprise support
The world's most popular data science platform