Vai al contenuto
AI.info

Tools

Milvus vs Weaviate

Milvus or Weaviate? Their plans monthly and yearly, the capabilities their makers state, security and latest updates, side by side — read from the makers' own pages.

In inglese

In short

  • Only Weaviate states: Choice of models, Self-hosted, API, Official SDKs, Runs models for you, Builds agents and workflows, Search over your data

Milvus

Open-source vector database for similarity search, hybrid retrieval, metadata filtering, and AI application data.

Plans

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)

Prices checked 2026-09-25 by web search.

Latest updates

  • milvus-3.0.2 (v3.0.2)

    Milvus v3.0.2 improves filtered search, group-by, and index-building performance and adds external collection and Storage V2 support.

  • milvus-2.6.24 (v2.6.24)

    Milvus v2.6.24 reduces peak memory during segment loading and improves force-merge planning and filtered search.

  • pkg/v3.0.2 (v3.0.2)

    Snapshot restores targeting the same collection are now serialized.

About Milvus

Weaviate

Weaviate is an open-source AI database for storing, searching, and retrieving vectorized data in self-hosted or managed deployments.

Plans

Free

Free

  • Always free — 1 cluster per user
  • 100,000 objects · 1 GB memory · 10 GB disk
  • 1 collection, up to 3 tenants
  • Embeddings (2,000 req/day) + Query Agent (1,000 req/mo)
  • Basic Support

Flex

  • Starts at $45 /mo
  • Pay-as-you-go, monthly, no commitment
  • Shared cloud cluster with full core DB toolkit + replication
  • Baseline security with RBAC
  • Highly available clusters — 99.5% uptime
  • Query Agent free tier + usage-based; Embeddings usage-based
  • Standard support — next-business-day Sev 1

Premium

Price on request

  • Prepaid contract with predictable spend
  • Choice of shared or dedicated deployment
  • Trusted reliability — up to 99.95% uptime
  • Global coverage on AWS, GCP & Azure
  • Query Agent free tier + usage-based; Embeddings usage-based
  • Enterprise support — as fast as 1-hour Sev 1 + dedicated Technical Account Team

Prices checked 2026-09-25 on the maker’s page.

Capabilities

  • Choice of models — “Seamlessly connect your data with models from a range of providers.” source
  • Self-hosted — “Weaviate’s open source AI database can be self-hosted or run as a managed service in Weaviate Cloud to reduce operational overhead.” source
  • API — “Use SDKs for Python, Go, TypeScript, or JavaScript, or connect to GraphQL or REST APIs.” source
  • Official SDKs — “Use SDKs for Python, Go, TypeScript, or JavaScript, or connect to GraphQL or REST APIs.” source
  • Runs models for you — “Access embedding models hosted in Weaviate Cloud. Simple, pay-as-you-go, GPU-powered.” source
  • Builds agents and workflows — “Pre-built agentic workflows that dynamically interact with your data in Weaviate to perform sync, async, and multi-step tasks.” source
  • Search over your data — “Store, index, and search high-dimensional vectors at any scale. The foundation for search, RAG, and agents.” source

Security

  • HIPAA — “Stay compliant with SOC 2, HIPAA, data privacy, and explainability.” source

Latest updates

About Weaviate