Pin high-QPS namespaces to cache
NEW: Pin namespaces for predictable cost and latency on high QPS workloads
Navigation
turbopuffer
Docs
Pricing
Customers
Blog
Talk to us
Log in
Sign up
contact sales
let's get puffin'
Vector Perf
Full-Text Perf
Workload
768 dimensions, 1M docs, ~3GB
p50
8ms
343ms
p90
10ms
444ms
p99
35ms
554ms
Warm namespace
Cold namespace
Approach (32 QPS with topk=10)
turbopuffer/tpuf-benchmark
Trusted by
Company
Jobs
Pricing
Store
Press & media
System status
Support
Slack
Docs
Email
Sales
Follow
Blog
RSS
Events
© 2026 turbopuffer Inc.
Terms of service
Data Processing Agreement
Privacy Policy
Security & Compliance
Docs search
esc
Guides
Quickstart
Get started with turbopuffer in minutes
Vector Search
Perform approximate nearest neighbor searches
Full-Text Search
Learn how to use BM25 full-text search
Hybrid Search
Combine vector and full-text search strategies
API Docs
Write
Create, update, or delete documents
Query
Query documents with filters and ranking
Auth & Encoding
Authentication, headers, and request encoding
Namespace metadata
Get metadata about a namespace
