AI and agents · by turbopuffer
turbopuffer
Keep a separate searchable library for each of thousands of customers.
embedding, search, data → data
- Way in
- Official APISign up yourself, api key
- To start
- $none
- Runs
- In the cloud
- Checked
- Nov 3, 2026Prices as of that day
What it can do 1
Store and query vectors/BM25 across many namespaces10 KB min write; 1.28 GB min per queryembedding, search, data → dataLaunch $16/mo min; storage <=$0.33/GB, writes <=$2/GB, queries <=$1/PB scanned
Does the same job
Prices and limits as of Nov 3, 2026, from turbopuffer’s own pages. They change; check before you rely on them.Not affiliated with turbopuffer. Not advice.Something wrong?