Milvus vs pgvector
Comparing two vector database platforms on pricing, features, free tier, and trade-offs.
Quick summary
Milvus — Open source vector database for GenAI. Milvus is a CNCF-graduated open-source vector database built for massive scale, with managed cloud via Zilliz.
pgvector — Vector similarity search for Postgres. pgvector is an open-source Postgres extension that adds vector similarity search to any Postgres database. Runs anywhere Postgres runs (Supabase, Neon, RDS).
Feature comparison
| Feature | Milvus | pgvector |
|---|---|---|
| Pricing model | Freemium | Free |
| Starting price | $65/mo (Zilliz) | Free (just Postgres) |
| Free tier | Yes | Yes |
| Open source | Yes | Yes |
| Type | Hybrid | Postgres extension |
| Free Tier | Zilliz free cluster | Unlimited |
| Serverless | Yes | No |
| Self-hosted | Yes | Yes |
| Multi-tenant | Yes | Yes |
| Hybrid Search | Yes | Yes |
| Max Dimensions | 32768 | 16000 |
| Metadata Filtering | Yes | Yes |
Milvus
Open source vector database for GenAI
Pros
- Scales to billions of vectors
- CNCF-graduated, enterprise-ready
- Multiple index types (HNSW, IVF, DiskANN)
- Strong in China / APAC market
Cons
- Heavy for small use cases
- Steep learning curve
- Ops complex if self-hosting
pgvector
Vector similarity search for Postgres
Pros
- Use your existing Postgres
- No new infrastructure
- Transactional guarantees with vectors
- Free — pay only for Postgres
Cons
- Slower than purpose-built vector DBs at scale
- Index build times grow with data
- Not ideal for 100M+ vectors
Which should you choose?
Choose Milvus if you value open source and want the option to self-host, and a free tier is important for your stage. Choose pgvector if you value open source and want the option to self-host, and a free tier is important for your stage.