Turbopuffer
Serverless vector and full-text search built on object storage, billed on a monthly minimum plus usage.
- Vector databases
- Not documented
- Launch plan: $16/month minimum usage, including all database features. Scale plan: $256/month minimum. Enterprise: $4,096+/month.
- Not documented
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.
Editorial · Palash Bagchi · approved
What the documentation says.
Each value below links to the page it was read from, with the sentence it came from. Criteria Turbopuffer does not publish are not listed.
Pricing
Entry paid plan
Launch plan: $16/month minimum usage, including all database features. Scale plan: $256/month minimum. Enterprise: $4,096+/month.
Sources (1) →Sources ↓
- Turbopuffer Pricing ↗
“$16/month minimum usage. Includes all database features. [Scale] $256. [Enterprise] $4,096+.”
Read 2026-09-11 · official pricing
Pricing model
Subscription with a monthly minimum per tier, plus usage-based overage charges beyond that minimum.
Sources (1) →Sources ↓
- Turbopuffer Pricing ↗
“Minimum monthly commitments ($16 Launch, $256 Scale, $4,096+ Enterprise), plus usage-based overage charges.”
Read 2026-09-11 · official pricing
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.
Sources (1) →Sources ↓
- Turbopuffer documentation ↗
“distance_metric="cosine_distance"”
Read 2026-09-11 · official docs
Hybrid search (vector + keyword)
Supported — combines vector search and BM25 full-text search to produce semantically relevant results.
Sources (1) →Sources ↓
- Turbopuffer documentation ↗
“turbopuffer supports vector search and BM25 full-text search. Combining them produces semantically relevant search results.”
Read 2026-09-11 · official docs
When these numbers change, hear about it. Sources are re-checked monthly; a repricing goes out as a short note.