Softwr

Machine Learning · head to head

Milvus vs Seldon

Milvus logo

Milvus

Machine Learning

Open-source vector database for scalable similarity search

From
Free
Rated
-
Full reviewWebsite
Seldon logo

Seldon

Machine Learning

Kubernetes model serving whose current version is licensed under the Business Source Licence

From
Free
Rated
-
Full reviewWebsite

The short version

  • Each has a real cost: Milvus vector dimensions are capped at 32,768; 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.
  • They diverge on capability: Milvus covers Billion-scale vectors, Seldon covers Kubernetes custom resources.
  • Prices and features above were last checked on 30 August 2026.

Where they differ

Only the attributes on which Milvus and Seldon actually diverge.

Attributes where Milvus and Seldon differ
AttributeMilvusSeldon
PlatformsLinux, Mac, Windows, WebLinux
Founded20172014

Identical on both: starting price (Free), pricing model (freemium), free tier (Yes), user rating (Not yet rated), category (Machine Learning).

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 Milvus

  • Billion-scale vectors
  • Multiple index types
  • GPU acceleration
  • Hybrid search
  • Data partitioning
  • PyTorch
  • TensorFlow
  • Hugging Face

Only in Seldon

  • Kubernetes custom resources
  • Inference graphs
  • Traffic strategies
  • Open Inference Protocol
  • Alibi Explain
  • Alibi Detect
  • Kafka-backed pipelines in v2
  • Commercial control plane

What people use each for

The jobs each tool is most often brought in to do.

Milvus

  • Self hosting a vector database for semantic searchnot Seldon
  • Storing and querying embeddings for retrieval augmented generationnot Seldon
  • Similarity search over images, audio or text at scalenot Seldon

Seldon

  • Serving an ensemble or a multi-stage inference path as one versioned deployment rather than as a chain of separate servicesnot Milvus
  • Running genuine production experiments where a share of live traffic goes to a candidate model and the results are comparednot Milvus
  • Regulated environments needing explanations and drift monitoring attached to the served model rather than bolted on laternot Milvus
  • Organisations with an established Kubernetes platform team who want serving expressed as manifests under existing deployment controlsnot Milvus

Where each one falls short

Documented limitations, not opinions. Every one is a constraint you would hit in normal use.

Milvus

  • Vector dimensions are capped at 32,768
  • A collection is limited to 64 fields, 1,024 partitions and 16 shards
  • Only 1 index is allowed per field
  • Search returns at most 16,384 vectors as top-k, and nq is capped at 16,384
  • Input and output per RPC is capped at 64 MB for insert, search and query
  • VARCHAR values are limited to 65,535 characters
  • Data loaded into query nodes cannot exceed 90% of available memory
  • An instance supports at most 65,536 collections

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.

Pricing, plan by plan

Milvus

Free
  • Open SourceFree
    • Full features
    • Self-hosted
    • Community support
  • Zilliz CloudFree
    • Managed service
    • Free tier available

Seldon

Free
  • Seldon CoreFree
    • Open source
    • Kubernetes deployment
    • Model serving
  • Seldon DeployFree
    • Enterprise features
    • GUI
    • Monitoring

Which should you pick?

Choose Milvus if

  • You need billion-scale vectors.
  • You want to start without paying.
  • You work on Linux, Mac, Windows, Web.
  • You also want multiple index types.
Milvus review

Choose Seldon if

  • You need kubernetes custom resources.
  • You want to start without paying.
  • You work on Linux.
  • You also want inference graphs.
Seldon review

Questions people ask

Is Milvus or Seldon better?
Neither clearly leads. Milvus starts at Free and Seldon at Free, and user ratings are close enough to be indistinguishable. Choose on capability and platform support.
Which is cheaper, Milvus or Seldon?
Milvus starts at Free and Seldon at Free.
Does Milvus or Seldon run on more platforms?
Milvus runs on Linux, Mac, Windows, Web. Seldon runs on Linux.
Can I use Milvus for free?
Both have a free tier, so you can try either at no cost before committing.
What is Milvus best used for?
Milvus is most often used for self hosting a vector database for semantic search, storing and querying embeddings for retrieval augmented generation, similarity search over images, audio or text at scale. Of those, self hosting a vector database for semantic search and storing and querying embeddings for retrieval augmented generation are not what Seldon is typically brought in for.
What can Milvus do that Seldon cannot?
Milvus covers Billion-scale vectors, Multiple index types, GPU acceleration, Hybrid search. Seldon covers Kubernetes custom resources, Inference graphs, Traffic strategies, Open Inference Protocol.

Answered from the vendors’ own pages

Milvus: How much does Milvus cost?

Milvus is open-source and free to use and modify. The self-hosted version has no licensing cost. Zilliz Cloud (the managed SaaS version) does not publish pricing on the website.

Source
Seldon: 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.

Milvus: Is there a free or open-source version of Milvus?

Yes, Milvus is fully open-source and available for free. Milvus Lite is a lightweight option for learning and prototyping that can be installed via pip.

Source
Seldon: 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.

Milvus: Does Milvus offer a managed cloud service?

Yes, Zilliz Cloud is a fully managed Milvus cloud offering with serverless and dedicated cluster options. Pricing must be requested from the company as it is not listed on the public website.

Source
Seldon: 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.

Seldon: 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.

Seldon: 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.

Share

Related pages

More on Milvus

More on Seldon

Keep looking

Other head to heads