Chroma vs turbopuffer
Two sides of the vector database decision: embedded / local-first and managed vector store. When each fits, what it costs, who moves from one to the other, and what makers who chose it say.
Which fits you
Choose Chroma if- You're prototyping retrieval on your laptop, or want vectors in files with no server
Use it whenYou're still figuring out whether retrieval works for your use case.
Trade-offFor production you either run its server yourself or move to Chroma Cloud.
Choose turbopuffer if- You want a hosted index with nothing to operate
Use it whenYou have many separate namespaces, such as one index per customer.
Trade-offNo free tier (paid plans have a monthly minimum), and it's cloud-only.
At a glance
| Chroma | turbopuffer | |
|---|---|---|
| Used by | 13 makers' products · 69 open-source projects | 8 makers' products · 7 open-source projects |
| Cost at default usagevectors stored 1 million vectors, queries 1 million queries, vectors written or updated 500k writes | $51/mo Starter | $21/mo Launch |
| Downloads | 236.5k/wk−12% vs npm | 1.1M/wk3.9× vs npm |
| Pricing | Free and open source to self-host (Apache-2.0); Chroma Cloud is usage-based with free starting credits. · paid from Usage-based | Usage-based tiers with a monthly minimum; higher tiers add SSO, audit logs, and enterprise/BYOC deployments. · paid from $16/mo minimum usage |
| Free tier | Yes | No |
| Open source | Yes · self-hostable | No |
| Incidents, 90 daysfrom its status page | no public status feed | 4 (4 major) |
Cost as you grow
At 100k vectors Chroma costs less ($1.32 vs $17); from about 1M vectors turbopuffer does ($21 vs $51). They're different kinds of tool — embedded / local-first and managed vector store — so the prices don't buy the same thing.
The numbers, plan by plan
| Vectors stored (1,536 dimensions, about 6 GB per million) | Chroma | turbopuffer |
|---|---|---|
| 0.1 | $1.32 Starter | $17 Launch |
| 0.5 | $15 Starter | $19 Launch |
| 1 | $51 Starter | $21 Launch |
| 5 | $1,093 Starter | $179 Launch |
| 10 | $4,281 Starter | $430 Launch |
| 50 | $105,226 Starter | $3,173 Launch |
| 100 | $419,999 Starter | $7,576 Scale |
From each vendor's pricing page: Chroma, turbopuffer.
What makers say
Makers on using it for vector database, from Product Hunt and Starter Story interviews, each linked to the source. Products with a page of their own and fuller notes first.
On ChromaChroma makes it super easy to manage embeddings for AI apps. We love the open-source focus and how quickly it integrates into RAG pipelines.
Jeff (the founder) is incredible - super knowledgeable and I'm super bullish on the direction of the product. Let's go!
Powered memory storage with a dead-simple, blazing-fast open-source vector DB. Far easier to self-host than alternatives.
On turbopufferNo maker quote about turbopuffer for vector database yet.
Loved and watch-outs
Themes that recur in makers' words and Hacker News comments, each linked to what it summarises.
Chroma- Open source and easy to self-host, with a simple API that gets embeddings stored quickly. PHHN
- Full-text and regex search sit alongside vector search, and collection forking suits changing code. trychroma.comHNHN 2HN 3
- Plugs quickly into RAG pipelines and local-first tools built on LangChain or Ollama. PHHNHN 2HN 3
turbopuffer- Storing vectors on object storage with a cache in front keeps large-scale search cheap. HNHN 2HN 3turbopuffer.com
- Handles hundreds of millions to billions of documents, a common next step when pgvector runs out. turbopuffer.comturbopuffer.com 2turbopuffer.com 3HN
- Operationally simple, with BM25, attribute filtering, recall tuning and consistency options built in. HNHN 2HN 3HN 4
Who uses each
Clarm
Conduit
Supaboard AI
VoltAgent
falWhat makers pair each with
With Chroma
MintlifyWith turbopuffer
Dub
Mastrapuppyone-cloudDub
LinearMastrapuppyone-cloudVision-AgentsMastraVision-AgentsMastrapuppyone-cloudMastrapuppyone-cloudNeither quite right?
See the whole vector database decision →
pgvectorInside your databaseApps already on Postgres that want vector search in the same database, joined with normal tables.
PineconeManaged vector storeA fully hosted index with nothing to operate, sized by usage.vs Chroma →vs turbopuffer →
QdrantOpen-source vector storeHeavy metadata filtering alongside vector search, self-hosted from one binary or on its managed cloud.vs Chroma →vs turbopuffer →
WeaviateOpen-source vector storeHybrid search that mixes keyword and vector results, with built-in modules that can create embeddings for you.