Milvus: Vector Databases

Founded 2017|San Francisco, California|51-200 people|Open Source

What is Milvus?

Milvus is an open-source vector database built for scalable similarity search, capable of handling billions of vectors in distributed environments. Created by Zilliz, a company founded in 2017 by Charles Xie (former founding engineer of Oracle 12c cloud database), Milvus has become one of the most widely deployed vector databases with over 30,000 GitHub stars.

The database supports multiple index types including IVF, HNSW, and DiskANN, with GPU-accelerated search and hybrid search combining dense and sparse vectors in a single query. Milvus runs on Kubernetes for production deployments and is governed under the LF AI & Data Foundation. Zilliz Cloud offers a fully managed version with automatic scaling, starting with a free tier and usage-based pricing from $4 per million vector compute units.

Zilliz has raised approximately $113-132 million in funding, with a $60 million Series B extension in August 2022 led by Prosperity7 Ventures (Aramco). The company is headquartered in San Francisco with roughly 140 employees. Zilliz was named "Highest Performer" and "Easiest to Use" in G2's Summer 2025 Vector Database Grid Report.

Key features

Core capabilities this platform advertises.

Billion-scale vector search
GPU-accelerated indexing
Distributed architecture
Multiple index types
Cloud and self-hosted options

Strengths and tradeoffs

What this tool does well, and the limitations to keep in mind.

Pros

Extreme scalability handling billions of vectors in distributed environments
Fully open-source under Apache 2.0 with no vendor lock-in
Hybrid search combining dense and sparse vectors in single queries
Rich index flexibility with IVF, HNSW, DiskANN and GPU acceleration
Managed cloud option reduces DevOps burden with auto-scaling

Cons

Complex distributed architecture requiring Kubernetes for production
Steep learning curve for index tuning and deployment configuration
High memory and storage requirements for large datasets
No in-place vector updates requiring delete and re-insert workarounds

Plans & pricing

What's included in each plan, and how the tiers compare.

Milvus (Open Source)

Free

Apache 2.0 license
Self-hosted on Kubernetes
Full feature access
Community support

Zilliz Cloud Free

5GB storage
2.5M vCUs/month
Up to 5 collections

Zilliz Cloud Standard

From $99/month

Up to 32 query CUs
Manual scaling
Email/ticket support

Zilliz Cloud Enterprise

From $155/month

99.95% uptime SLA
SSO and RBAC
24/7 enterprise support
VPC peering

View official pricing page

Common use cases

Organizations that need vector search at billion-scale with high throughput

Billion-vector similarity search
Large-scale recommendation systems
Image and video retrieval
Genomics and scientific computing
Enterprise-scale RAG systems

Using Milvus with Respan

Respan complements Milvus by providing observability for the LLM layer in RAG (Retrieval-Augmented Generation) pipelines. Teams using Milvus for vector search can monitor the end-to-end AI pipeline including embedding generation, retrieval quality, and LLM response generation through Respan.

Monitor RAG pipeline performance from embedding to generation
Track LLM costs in Milvus-powered retrieval workflows
Evaluate retrieval quality and LLM response accuracy
Optimize embedding model selection for vector search quality

Run Milvus in production with Respan

10KFree traces/mo

1,000+Models

5 minSetup

Respan lets you trace LLM and agent calls across any model or framework, A/B test prompts on production traffic, and route requests across 1,000+ models through one gateway.

Try Respan free

Best Milvus alternatives & competitors

Top companies in Vector Databases you can use instead of Milvus.

Pinecone

Fully managed serverless vector database