# Turbopuffer

Canonical: https://inetgeek.com/vector-db/turbopuffer/

Serverless vector and full-text search built on object storage, billed on a monthly minimum plus usage.

## Who it suits

Teams that want vector search billed like storage rather than compute — object-storage-backed pricing tends to undercut memory-resident vector databases at rest, especially for large, cold datasets.

Consider something else if The full list of supported similarity metrics matters before committing — that wasn't fully documented in what's sourced here, unlike competitors that publish the complete list.

## What the documentation says

### Pricing

- Entry paid plan: Launch plan: $16/month minimum usage, including all database features. Scale plan: $256/month minimum. Enterprise: $4,096+/month. ([source](https://turbopuffer.com/pricing), read 2026-09-11)
- Pricing model: Subscription with a monthly minimum per tier, plus usage-based overage charges beyond that minimum. ([source](https://turbopuffer.com/pricing), read 2026-09-11)

### Vector

- Similarity metrics supported: Cosine distance is documented as a supported metric (used in the SDK's example code); the full list of supported metrics wasn't confirmed beyond this. ([source](https://turbopuffer.com/docs/hybrid-search), read 2026-09-11)
- Hybrid search (vector + keyword): Supported — combines vector search and BM25 full-text search to produce semantically relevant results. ([source](https://turbopuffer.com/docs/hybrid-search), read 2026-09-11)

## Compared with

- [Turbopuffer vs Pinecone](https://inetgeek.com/compare/turbopuffer-vs-pinecone/)
- [Turbopuffer vs Qdrant](https://inetgeek.com/compare/turbopuffer-vs-qdrant/)
- [Turbopuffer vs Weaviate](https://inetgeek.com/compare/turbopuffer-vs-weaviate/)
- [Turbopuffer vs Redis Cloud](https://inetgeek.com/compare/redis-cloud-vs-turbopuffer/)
- [Turbopuffer vs Elastic Cloud](https://inetgeek.com/compare/elastic-cloud-vs-turbopuffer/)