Softwr

Databases · head to head

Chroma vs turbopuffer

Chroma logo

Chroma

Databases

Apache 2.0 vector and full-text search engine that runs as an embedded library, a single server or a distributed cloud service.

From
Free
Rated
-
Full reviewWebsite
turbopuffer logo

turbopuffer

Databases

Closed-source vector and full-text search service built directly on object storage, with cold queries measured in seconds rather than milliseconds.

From
$16/month
Rated
-
Full reviewWebsite

The short version

  • Only Chroma has a free tier, so it costs nothing to try first.
  • Each has a real cost: Chroma on a single node, available memory sets a hard upper bound on collection size, roughly 245,000 records per gigabyte of RAM at 1024 dimensions, so capacity planning is a memory purchase and the ceiling arrives without warning.; turbopuffer a cold namespace pays object storage latency on the first query, with a documented p90 around 1,214 ms on a million documents, so any interactive search box needs the data kept warm or the user waits about a second.
  • They diverge on capability: Chroma covers Embedded mode, turbopuffer covers Object storage architecture.
  • Prices and features above were last checked on 30 August 2026.

Where they differ

Only the attributes on which Chroma and turbopuffer actually diverge.

Attributes where Chroma and turbopuffer differ
AttributeChromaturbopuffer
Starting priceFree$16/month
Pricing modelusage-basedsubscription
Free tierYesNo

Identical on both: platforms (Web), user rating (Not yet rated), category (Databases).

What each one covers

Drawn from each product's published feature list. An absence here means we hold no record of it - not that the product lacks it.

Only in Chroma

  • Embedded mode
  • Single-node server
  • Distributed architecture
  • Metadata filtering
  • Consistent API across modes
  • Multi-language clients
  • Embedding function integrations
  • Apache 2.0 licence

Only in turbopuffer

  • Object storage architecture
  • Namespaces
  • Attribute filtering
  • Documented limits
  • Configurable consistency
  • Durable writes
  • Multi-query requests
  • Deployment options

Both cover

  • Vector search
  • Full-text search

What people use each for

The jobs each tool is most often brought in to do.

Chroma

  • Prototyping retrieval-augmented generation where the priority is having a working index in minutes rather than choosing a permanent storenot turbopuffer
  • Agent memory in a single application process, where an embedded store avoids adding a network dependencynot turbopuffer
  • A departmental search application under roughly ten million records where one server is sufficient and simplicity is worth more than headroomnot turbopuffer
  • Local and CI testing of retrieval code with the same client library used in productionnot turbopuffer

turbopuffer

  • A product with one search index per customer and thousands of customers, most of whose data is idle on any given daynot Chroma
  • Very large corpora where holding every vector in memory is the dominant cost and occasional cold-query latency is acceptablenot Chroma
  • Hybrid retrieval combining BM25 and vector search where running and synchronising two separate systems is the problem being solvednot Chroma
  • Retrieval for agent and assistant products where indexes are created and destroyed frequently and per-index overhead must be near zeronot Chroma

Where each one falls short

Documented limitations, not opinions. Every one is a constraint you would hit in normal use.

Chroma

  • On a single node, available memory sets a hard upper bound on collection size, roughly 245,000 records per gigabyte of RAM at 1024 dimensions, so capacity planning is a memory purchase and the ceiling arrives without warning.
  • Single-node queries parallelise only up to the number of vCPUs, after which requests queue and latency rises linearly with concurrency, so throughput problems appear as a slow application rather than as errors.
  • The distributed deployment behind Chroma Cloud is a different architecture from the embedded library, so latency, consistency and failure behaviour observed in a local prototype do not predict production behaviour.
  • The open source server has no built-in authentication or multi-tenancy worth relying on, so a self-hosted deployment needs its own auth proxy and network controls before anything untrusted can reach it.
  • The project has moved quickly through major internal rewrites and version changes, so upgrades have historically involved data migrations and client changes, and pinning versions is necessary rather than cautious.

turbopuffer

  • A cold namespace pays object storage latency on the first query, with a documented p90 around 1,214 ms on a million documents, so any interactive search box needs the data kept warm or the user waits about a second.
  • Queries are eventually consistent by default, and after roughly 128 MiB of outstanding writes new data is invisible until indexed, which the vendor puts at tens of seconds for small namespaces and tens of minutes for large ones, so a bulk re-index is not immediately queryable.
  • It is closed source with no community edition, so single-tenant or bring-your-own-cloud deployment is a commercial negotiation rather than a deployment choice, and there is no path to running it yourself if the relationship ends.
  • Per-namespace ceilings, roughly 10,000 writes per second, 32 MB/s and 500 million documents per shard, mean a single enormous index has to be sharded across namespaces by your application rather than by the service.
  • It is a search engine, not a database: there are no joins, no cross-document transactions and no SQL, so it sits beside a primary datastore and keeping the two in step is work that belongs to you.

Pricing, plan by plan

Chroma

Free
  • StarterFree
    • 10 databases
    • 10 team members
    • Community Slack access
  • Team$250/month
    • 100 databases
    • 30 team members
    • $100 in included credits
  • Enterprise$null/month
    • Unlimited databases
    • Unlimited team members
    • Dedicated support

turbopuffer

$16/month
  • Launch$16/month
    • All database features
    • Multi-tenancy deployment
    • SOC2 & GDPR-ready DPA
  • Scale$256/month
    • Everything in Launch
    • HIPAA-ready BAA
    • Single Sign-On (SSO)
  • Enterprise$4096/month
    • Everything in Scale
    • Single-tenancy & BYOC deployment options
    • Private networking

Which should you pick?

Choose Chroma if

  • You need embedded mode.
  • You want to start without paying.
  • You also want single-node server.
Chroma review

Choose turbopuffer if

  • You need object storage architecture.
  • You also want namespaces.
turbopuffer review

Questions people ask

Is Chroma or turbopuffer better?
Neither clearly leads. Chroma starts at Free and turbopuffer at $16/month, and user ratings are close enough to be indistinguishable. Choose on capability and platform support.
Which is cheaper, Chroma or turbopuffer?
Chroma has a free tier; the other does not. Paid plans start at Free for Chroma and $16/month for turbopuffer.
Does Chroma or turbopuffer run on more platforms?
Both run on Web, so platform support will not decide this one for you.
Can I use Chroma for free?
Yes. Chroma has a free tier, so you can try it without paying. turbopuffer starts at $16/month.
What is Chroma best used for?
Chroma is most often used for prototyping retrieval-augmented generation where the priority is having a working index in minutes rather than choosing a permanent store, agent memory in a single application process, where an embedded store avoids adding a network dependency, a departmental search application under roughly ten million records where one server is sufficient and simplicity is worth more than headroom, local and ci testing of retrieval code with the same client library used in production. Of those, prototyping retrieval-augmented generation where the priority is having a working index in minutes rather than choosing a permanent store and agent memory in a single application process, where an embedded store avoids adding a network dependency are not what turbopuffer is typically brought in for.
What can Chroma do that turbopuffer cannot?
Chroma covers Embedded mode, Single-node server, Distributed architecture, Metadata filtering. turbopuffer covers Object storage architecture, Namespaces, Attribute filtering, Documented limits. Both handle Vector search, Full-text search.

Answered from the vendors’ own pages

Chroma: Do I need to run a server?

No. Chroma runs embedded in your process with persistence to a local directory, which is how most projects start. The server and distributed modes exist for when multiple clients or larger collections require them.

turbopuffer: Can I self-host turbopuffer?

There is no open source or community edition. Single-tenant and bring-your-own-cloud deployments exist as commercial arrangements, but there is no way to run it independently of the vendor.

Chroma: How large can a single node get?

The project puts single-node deployments at fewer than about ten million records across a handful of collections, with collection size bounded by system memory at roughly 245,000 records per gigabyte at 1024 dimensions.

turbopuffer: How fast is it really?

Warm queries perform comparably to in-memory search engines. Cold queries, where data is not cached, have a documented p90 around 1,214 ms on a million documents. Write p90 is around 248 ms for a 512 KB upsert because writes go straight to object storage.

Chroma: Is Chroma Cloud the same software?

It is the same API and project, but the distributed deployment is a different architecture, using independent services, object storage and SSD caches rather than a single process. Behaviour under load differs accordingly.

turbopuffer: Is it consistent?

Eventually consistent by default, with the vendor reporting that over 99.8% of queries return consistent data. Strong consistency can be requested per query at a latency cost. Large write bursts have a longer visibility delay while indexing catches up.

Chroma: How does it compare with pgvector?

pgvector keeps vectors in a Postgres database you already operate, with SQL, joins and transactions. Chroma is a dedicated retrieval engine with a lower setup cost and a retrieval-shaped API. If you already run Postgres, pgvector removes a system; if you do not, Chroma removes a decision.

turbopuffer: What is it best at?

Large numbers of namespaces where most are idle. The architecture makes cold data cheap to keep, which is exactly the shape of a multi-tenant product with a long tail of inactive customers.

Chroma: What licence is it under?

Apache 2.0, which permits self-hosting and embedding in commercial products without a competing-use restriction.

turbopuffer: What are the hard limits?

Up to 128 billion documents and 256 TB per namespace, 500 million documents per shard, 64 MiB per document, 10,752 dense vector dimensions, roughly 10,000 writes per second per namespace and a maximum result set of 10,000.

Share

Related pages

More on Chroma

More on turbopuffer

Keep looking

Other head to heads