AI Tools
Milvus
Milvus : prix, capacités, mises à jour et alternatives, lus sur les pages de l’éditeur.

En anglais
Key facts
- Price
- Free Read on milvus.io
- Free plan
- Yes Read on milvus.io
- Platforms
- Web · macOS · Windows · Linux · CLI · API
- API
- Yes Read on milvus.io
- Open source
- Yes Read on github.com
- Latest version
- v3.0.6 Read on milvus.io
- Last update
- 10 Nov 2026 Read on github.com
- Prices checked
- 25 Oct 2026 Read on milvus.io
Milvus stores vector embeddings and supports similarity search, metadata filtering, and deployments ranging from a local library to distributed clusters. Developers use it for retrieval in AI applications, recommendations, and multimedia search.
Milvus is database software, not a hosted service by itself. Self-hosting requires infrastructure; Zilliz Cloud is a separate managed option. The official pricing page could not be read, so its tiers and prices are unconfirmed.
- Category
- Developer Tools
- Read from the maker’s pages
- 2026-11-18
Company
Features
- Store vector embeddings and run approximate nearest-neighbor searches
- Filter search results using metadata
- Choose local, standalone, or distributed deployment
- Scale distributed deployments across machines
- Use APIs and SDKs to connect applications
- Run Milvus CLI commands to manage collections, indexes, and data
- Open-source under Apache License 2.0
Use cases
- Build semantic retrieval for a retrieval-augmented generation system
- Find similar images, videos, or audio files
- Retrieve relevant documents from an organization's knowledge base
- Recommend items by comparing user and item embeddings
- Detect unusual patterns in vectorized data
Pricing
Free
- Prices checked
- 2026-10-25
Milvus (Open Source)
free
- 100% free open-source project under Apache License 2.0
- Self-hosted deployments (Lite, Standalone, Distributed)
- No usage limits from the software itself (hardware-dependent)
Capabilities
- Command line — “Milvus CLI” source
- Self-hosted — “Milvus Distributed can be deployed on Kubernetes clusters, featuring a cloud-native architecture designed for billion-scale or even larger scenarios.” source
- API — “RESTful API (official)” source
- Official SDKs — “PyMilvus (Python SDK) (official)” source
- Search over your data — “These vectors are then stored in a vector database, enabling fast and scalable searches and analytics.” source
Latest updates
- pkg/v3.0.6: fix: [3.0] Fix added-field load hints on 3.0 (#55306)
Fixed added-field load hints so new fields are added according to schema defaults before schema publication.
- milvus-3.0.5
Added per-resource-group load percentage and shard-leader readiness in QueryCoord, with shard leaders tagged for same-group query routing.
- milvus-3.0.4
Speeds up bulk import, compaction, and filtered and grouped search; adds lazy column-group loading for Storage V3 and fixes hangs and access control issues.
- milvus-2.6.26
Speeds up RPC message decoding, reduces Proxy memory use for large search and query requests, and fixes crashes, hangs, and timestamp issues.
- milvus-3.0.5
Adds resource-group-aware load status in QueryCoord, reduces memory use, and fixes stability issues around coordinator restarts, rolling upgrades, and etcd errors.
Where it works
Web · macOS · Windows · Linux · CLI · API
Alternatives to Milvus
- Qdrant
Qdrant stores and searches vector data for semantic, similarity, keyword, and hybrid retrieval in AI applications.
- Zilliz Cloud
Managed vector database for storing, indexing, and searching embeddings in AI applications.
- Weaviate
Weaviate is an open-source vector database for storing and searching data in AI applications, with self-hosted and managed cloud options.
- Chroma
Open-source search infrastructure for AI apps, with vector, full-text, regex, and metadata search.
- Pinecone
Pinecone is a managed vector database for semantic, keyword, and hybrid search in AI applications.
- Mem0
Mem0 gives AI agents and apps persistent memory by extracting facts from conversations and retrieving relevant context later.
More from Zilliz
- Zilliz Cloud
Managed vector database for storing, indexing, and searching embeddings in AI applications.
Questions about Milvus
Is Milvus free?
Yes. The maker’s pages state that Milvus can be used for free. Read on the maker’s pages on 18 Nov 2026.
How much does Milvus cost?
The plans on the maker’s pricing page: Milvus (Open Source) (free). Prices checked on 25 Oct 2026.
Does Milvus have an API?
Yes. The maker’s pages state that Milvus has an API. Read on the maker’s pages on 18 Nov 2026.
Which platforms does Milvus run on?
Milvus runs on Web, macOS, Windows, Linux, CLI and API, as its maker’s pages state. Read on the maker’s pages on 18 Nov 2026.
Is Milvus open source?
Yes. The code of Milvus is published at github.com/zilliztech/attu. Read on the maker’s pages on 18 Nov 2026.
Is Milvus still available?
Yes, as of 18 Nov 2026: its maker’s pages were read that day and carried no notice that Milvus has ended.
What changed recently in Milvus?
The latest entry in its maker’s changelog: 10 Nov 2026, “pkg/v3.0.6: fix: [3.0] Fix added-field load hints on 3.0 (#55306)”. Before it: 10 Nov 2026, “milvus-3.0.5”. Changelog checked on 19 Nov 2026.
Sources
- https://milvus.io/pricing — Tried the official pricing page; it returned 404, so no tiers or prices could be read.
- https://milvus.io/ — Product page describes Milvus as an open-source vector database and lists deployment options.
- https://milvus.io/intro — Product overview describes vector search, filtering, APIs, indexing, and example use cases.
- https://milvus.io/docs/product_faq.md — FAQ states Milvus is free open-source software under Apache License 2.0 and identifies Zilliz Cloud as a separate managed option.
- https://milvus.io/docs/release_notes.md — Release notes identify v3.0.5, dated October 30, 2026, and summarize its changes.
Not confirmed
- Prices
- the official pricing URL returned 404; no pricing tiers or prices were readable
- the official pricing page could not be read