Turbopuffer
Object-storage-first vector DB. Powers Notion and Cursor. SPFresh indexing; ~10× cost reduction vs. memory-resident peers.
Active · Verified 2026-10-27 · fresh as of 2026-10-27 · 43 cited facts, 4 with a third-party source · 1 recorded change · Suggest a correction
At a glance
- Type
- Object-storage-first vector DB vendor fix
- Tier
- T1
- Section
- Vector-database infrastructure
- Latest release
- not applicable — not OSS fix
- License
- not applicable — not OSS fix
- GitHub
- not applicable — no GitHub repo fix
- Pricing
- Usage-based with monthly minimums: Launch $16/month, Scale $256/month, Enterprise from $4,096/month (35% usage premium); calculator rates storage up to $0.33/GB, writes up to $2.00/GB, queries up to $1.00/PB vendor fix
- Funding
- Seed+ · 2025-12 third-party fix
- Freshness
- 2026-10-27 fix
- Layer
- model-infra repo fix
- Licensing
- commercial vendor fix
- SDK languages
- csharp, go, java, python, rest, ruby, rust, typescript vendor fix
- Compliance
- ccpa, gdpr, hipaa, soc2-type2 vendor fix
When to use
Optimised for: low-latency similarity search + scale
Anti-fit: not for relational / graph-heavy queries (vector-first by design)
Pros & cons
Pros
Object-storage-backed vector DB at order-of-magnitude lower cost than peers; excellent for write-once-read-rarely memory.
Cons
Latency is higher than RAM-resident DBs; newer product with limited operational track record.
Claims & capabilities
Production scale: 3.5T+ documents, 10M+ writes/s, 25k+ queries/s; up to 100B vectors at 200ms P99; sub-10ms P50 latency; reports 95% cost reduction switching from traditional vector DBs (object-storage at $0.02/GB vs $0.60/GB); customers include Cursor, Notion, Linear, Anthropic; revenue 10x and headcount 5x in 2024–2025
Technical surface
- API surface
- REST, SDK: Python, TS, Go
- Backend storage
- custom (object-storage native vector engine)
- Deployment
- Managed-only — multi-tenant cloud; single-tenant and BYOC (in customer cloud) on Enterprise
- Embedding model
- BYO
- Multi-tenancy
- namespace
- MCP
- no first-party MCP adapter published as of 2026-05; community connectors may exist.
- A2A
- no Google A2A (Agent2Agent) integration documented as of 2026-05.
- OpenTelemetry
- no first-party OpenTelemetry exporter documented; standard logs/metrics typically available.
Alternatives to Turbopuffer → live options ranked by shared design, licence, hosting and MCP support
Similar systems
Other vector-database infrastructure in the catalog, ranked by inbound references.
- Qdrant T1
Distribution-Based Score Fusion + RRF. Sparse vectors native; filtering via ANN graph modification.
- Chroma T1
Limited native hybrid (users build RRF custom). Fast Rust core (v2.5). Acquired by Replit (definitive agreement announced 2026-10-23); Chroma Cloud is winding down (writes disabled 2026-11-22, reads disabled 2026-12-22) while open-source ChromaDB continues under Apache-2.0.
- pgvector T1
Stores embeddings alongside relational + full-text data. HNSW + IVFFlat ANN indexes. Used as agent conversation memory via LangChain + MCP. Foundation of Supabase AI and many self-hosted RAG stacks.
- Weaviate T1
Hybrid Search 2.0 with learned ranking. BM25 + vector in unified index.
- Milvus T1
Multi-vector columns (10 simultaneous). Native hybrid search (v2.5). CAGRA + Vamana GPU/CPU (v2.6).
- Pinecone T1
Managed vector DB. Cascading sparse + dense + rerank pipeline; pinecone-rerank-v0 .
Sources (42 cited facts, 4 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is Object-storage-first vector DB vendor
- What it does & what's distinct Object-storage-first vector DB. Powers Notion and Cursor. SPFresh indexing; ~10× cost re… vendor
- Claims / benefits Production scale: 3.5T+ documents, 10M+ writes/s, 25k+ queries/s; up to 100B vectors at … vendor
- Modalities text vendor
- Created 2023 vendor
- Mindshare 2 press ~15 (small star jobs third-party
- Funding Seed+ · 2025-12 third-party
- Customers / scale 1-10 ppl Anthropic, Atlassian, Cursor, Notion third-party
- Pricing Usage-based with monthly minimums: Launch $16/month, Scale $256/month, Enterprise from $… vendor
- Compliance SOC 2 Type II; HIPAA; GDPR-compliant vendor
- Deployment Managed-only — multi-tenant cloud; single-tenant and BYOC (in customer cloud) on Enterpr… vendor
- HQ CA third-party
- Founders / pedigree Simon Hørup Eskildsen (CEO, ex-Shopify principal engineer). vendor
- Memory volume / scale no scale claim vendor
- Performance Turbopuffer benchmark: 100M-vector queries at <100ms p95 from object storage (S3-backed … vendor
- API surface REST, SDK: Python, TS, Go vendor
- Latency p50/p99 p50 query ~16ms, p99 <1s (vendor) vendor
- Backend storage custom (object-storage native vector engine) vendor
- Multi-tenancy namespace vendor
- Encryption at-rest + in-transit vendor
- Embedding model BYO vendor
- Versioning immutable append-log vendor
- Schema evolution schema with migration vendor
- Namespace primitives per-tenant vendor
- Contradiction handling always overwrite (last-write-wins) vendor
- Forgetting policy none (permanent) vendor
- Webhooks / events no vendor
- Import / export JSON via REST; namespace upsert/query; Parquet ingest beta vendor
- Validated verticals RAG developers, agent builders (broad horizontal); financial-services, healthcare, legal… vendor
- Time to running <10min (managed cloud) to <1hr (self-host Docker) vendor
- Anti-fit not for relational / graph-heavy queries (vector-first by design) vendor
- Optimised for low-latency similarity search + scale vendor
- Adjacent infrastructure BYO embedding model + LLM; this IS the vector store vendor
- Pros Object-storage-backed vector DB at order-of-magnitude lower cost than peers; excellent f… vendor
- Cons Latency is higher than RAM-resident DBs; newer product with limited operational track re… vendor
- Project & sources turbopuffer.com docs vendor
- architecture-deployment-locus cloud vendor
- licensing-bucket commercial vendor
- positioning-platform-vs-product platform vendor
- taxonomy-three-layer-rollup model-infra repo
- compliance-certifications ccpa,gdpr,hipaa,soc2-type2 vendor
- sdk-languages csharp,go,java,python,rest,ruby,rust,typescript vendor
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)
- 2026-10-27
- Pricing “Pay-per-use” → “Usage-based with monthly minimums: Launch $16/month, Scale $256/month, Enterprise from $4,096/month (35% usage premium); calculator rates storage up to $0.33/GB, writes up to $2.00/GB, queries up to $1.00/PB” source
- Deployment “Hybrid” → “Managed-only — multi-tenant cloud; single-tenant and BYOC (in customer cloud) on Enterprise” source
Related systems
Referenced by (3)
- LangChain (framework) integrates with — LangChain docs have a turbopuffer vector store integration page. (verified 2026-10-29)
- Mastra integrates with — Mastra repo ships the @mastra/turbopuffer vector store package. (verified 2026-10-29)
- Mem0 integrates with — Mem0 docs have a Turbopuffer vector store page for Mem0 open source. (verified 2026-10-29)