Software · head to head
Seldon vs BentoML
The short version
- Each has a real cost: Seldon production deployment requires a Kubernetes cluster, whether managed such as GKE, EKS or AKS, or on-premises such as OpenShift; BentoML core BentoML framework is Apache 2.0 and free, but the managed BentoCloud enterprise tier has no published pricing: the README instructs buyers to sign up for personal access or contact sales for enterprise use, with no rate card shown.
- They diverge on capability: Seldon covers Model serving, BentoML covers Model packaging.
Where they differ
Only the attributes on which Seldon and BentoML actually diverge.
Identical on both: starting price (Free), pricing model (freemium), free tier (Yes), user rating (Not yet rated), category (Unknown).
What each one covers
Drawn from each product's published feature list. An absence here means we hold no record of it - not that the product lacks it.
Only in Seldon
- Model serving
- A/B testing
- Canary deployments
- Outlier detection
- Model explainability
- Kubernetes
- Istio
- Prometheus
Only in BentoML
- Model packaging
- REST API generation
- Adaptive batching
- Multi-framework support
- Container deployment
- PyTorch
- TensorFlow
- scikit-learn
Both cover
- Linux support
What people use each for
The jobs each tool is most often brought in to do.
Seldon
- Serving and routing machine learning models on Kubernetesnot BentoML
- Building multi-step inference pipelines with A/B tests and explainersnot BentoML
BentoML
- Machine learningnot Seldon
- Data analysisnot Seldon
- Model trainingnot Seldon
- Predictive analyticsnot Seldon
Where each one falls short
Documented limitations, not opinions. Every one is a constraint you would hit in normal use.
Seldon
- Production deployment requires a Kubernetes cluster, whether managed such as GKE, EKS or AKS, or on-premises such as OpenShift
- The documented components carry both minimum and maximum supported versions, so newer Kubernetes and dependency versions are not automatically supported
- Dataflow Pipelines need an additional component that the docs recommend avoiding installing when pipelines are not used
- The Docker Compose install is offered as a lightweight alternative for environments without Kubernetes rather than as a production path
BentoML
- Core BentoML framework is Apache 2.0 and free, but the managed BentoCloud enterprise tier has no published pricing: the README instructs buyers to sign up for personal access or contact sales for enterprise use, with no rate card shown.
Pricing, plan by plan
Seldon
Free- Seldon CoreFree
- Open source
- Kubernetes deployment
- Model serving
- Seldon DeployFree
- Enterprise features
- GUI
- Monitoring
BentoML
Free- Open SourceFree
- Model packaging
- API creation
- Local serving
- BentoCloudFree
- Managed deployment
- Auto-scaling
- Monitoring
Which should you pick?
Choose Seldon if
- You need model serving.
- You want to start without paying.
- You work on Linux.
- You also want a/b testing.
Choose BentoML if
- You need model packaging.
- You want to start without paying.
- You work on Linux, Mac, Windows.
- You also want rest api generation.
Questions people ask
- Is Seldon or BentoML better?
- Neither clearly leads. Seldon starts at Free and BentoML at Free, and user ratings are close enough to be indistinguishable. Choose on capability and platform support.
- Which is cheaper, Seldon or BentoML?
- Seldon starts at Free and BentoML at Free.
- Does Seldon or BentoML run on more platforms?
- Seldon runs on Linux. BentoML runs on Linux, Mac, Windows.
- Can I use Seldon for free?
- Both have a free tier, so you can try either at no cost before committing.
- What is Seldon best used for?
- Seldon is most often used for serving and routing machine learning models on kubernetes, building multi-step inference pipelines with a/b tests and explainers. Of those, serving and routing machine learning models on kubernetes and building multi-step inference pipelines with a/b tests and explainers are not what BentoML is typically brought in for.
- What can Seldon do that BentoML cannot?
- Seldon covers Model serving, A/B testing, Canary deployments, Outlier detection. BentoML covers Model packaging, REST API generation, Adaptive batching, Multi-framework support. Both handle Linux support.