Best forA fully hosted index with nothing to operate, sized by usage.
Trade-offClosed source and cloud-only, so leaving means re-indexing somewhere else.
Used by 53 makers' products for this
For vector database, the alternatives to Faiss that makers' products we track chose most are Pinecone (53), Qdrant (18) and Weaviate (16). 11 of the 14 are open source or self-hostable (Qdrant, Weaviate, Chroma and 8 more) and 9 have a free tier. At 10,000 users, the cheapest is turbopuffer at $21 a month on Launch.
Not a ranking: each option is described by the situation it fits, with its trade-off.
How many makers' products we track use each for vector database, and what each costs at 10,000 users.
| Option | Kind | Makers' products | At 10,000 users | Free tier | Open source | |
|---|---|---|---|---|---|---|
| Embedded / local-first | 0 | — | Yes | Yes | ||
| Managed vector store | 53 | $113/mo · Standard | Yes | No | ||
| Open-source vector store | 18 | $103/mo · Standard (3 nodes, 0.5 vCPU / 4 GiB each) | Yes | Yes | ||
| Open-source vector store | 16 | $253/mo · Flex | Yes | Yes | ||
| Embedded / local-first | 12 | $51/mo · Starter | Yes | Yes | ||
| Managed vector store | 8 | $21/mo · Launch | No | No | ||
| Inside your database | 1 | — | Yes | Yes | ||
| Embedded / local-first | 3 | — | Yes | Yes | ||
| Inside your database | 0 | — | Yes | Self-hostable | ||
| Managed vector store | 0 | — | Yes | No | ||
| Open-source vector store | 0 | — | Yes | Yes | ||
| Open-source vector store | 0 | — | No | Yes | ||
| Inside your database | 0 | — | No | Self-hostable | ||
| Inside your database | 0 | — | No | Self-hostable | ||
| Inside your database | 0 | — | — | Self-hostable |
Inside the database you already run, or a separate vector store. pgvector keeps vectors next to your rows, with one backup and one query language, but tuning large indexes is on you. A dedicated vector store handles scale, filtering and hybrid search for you, at the cost of another service to sync data into.
Faiss (Embedded / local-first): A fast in-memory vector index library for research, batch jobs and apps that load their index at startup. Trade-off: A library, not a database — no metadata filtering service, persistence or updates beyond what you build.
Best forA fully hosted index with nothing to operate, sized by usage.
Trade-offClosed source and cloud-only, so leaving means re-indexing somewhere else.
Used by 53 makers' products for this
Best forHeavy metadata filtering alongside vector search, self-hosted from one binary or on its managed cloud.
Trade-offOne more service to deploy and keep in sync with your main database.
Used by 18 makers' products for this
Best forHybrid search that mixes keyword and vector results, with built-in modules that can create embeddings for you.
Trade-offMore concepts and configuration to learn than simpler stores; some advanced features need a license key.
Used by 16 makers' products for this
Best forPrototyping RAG on your laptop with a pip or npm install and no server to run.
Trade-offFor production you either run its server yourself or move to Chroma Cloud.
Used by 12 makers' products for this
Best forVery large or many-tenant indexes where storing everything on object storage keeps cost down.
Trade-offNo free tier (paid plans have a monthly minimum), and it's cloud-only.
Used by 8 makers' products for this
Best forApps already on Postgres that want vector search in the same database, joined with normal tables.
Trade-offIndex tuning and memory sizing are your job, and very large indexes can crowd out the rest of the database.
Used by 1 maker's product for this
Best forAn embedded vector database that stores vectors and data as files on local disk or object storage, with no server to run.
Trade-offMany concurrent writers need care, and the managed cloud is a separate paid product.
Used by 3 makers' products for this
Best forApps already on MongoDB Atlas that want vector search on the same documents, with no second store to sync.
Trade-offVector search is most mature on Atlas; on self-hosted MongoDB it arrived later, so check your version and setup.
No maker product tracked for this yet
Best forA serverless vector index billed per request, alongside Upstash Redis and QStash, reached over HTTP from edge functions.
Trade-offClosed source and hosted only; per-request pricing gets expensive at very high query volume.
No maker product tracked for this yet
Best forVery large collections — hundreds of millions of vectors and up — on a distributed open-source database, or managed as Zilliz Cloud.
Trade-offThe distributed deployment has many moving parts; for small apps it's more system than you need.
No maker product tracked for this yet
Best forSearch and recommendations that combine vector, keyword and structured filters with custom ranking models, at large scale.
Trade-offMore concepts to learn (schemas, rank profiles, application packages) than a plain vector store; self-hosting means running a distributed system.
No maker product tracked for this yet
Best forVector search next to transactional and analytical SQL in one MySQL-compatible database.
Trade-offThe free workspace is for non-production use only; production starts at $0.99/hour, and self-managed editions go through sales.
No maker product tracked for this yet
Best forCombining graph traversals with vector search in one query, for GraphRAG, fraud or recommendation work on connected data.
Trade-offA graph database first, with its own query language (GSQL) to learn; managed pricing is usage-based after a free trial.
No maker product tracked for this yet
Best forGraph, document and vector search in one multi-model database queried with AQL.
Trade-offCommunity Edition is free only for evaluation and non-commercial use; Enterprise Edition and the managed cloud are priced on request.
No maker product tracked for this yet
It depends on what you need it for; we don't rank them. The one makers' products we track chose most for vector database is Pinecone (53 makers' products). You already use Postgres and have up to a few million vectors: pgvector. You're prototyping retrieval on your laptop, or want vectors in files with no server: Chroma. You want a hosted index with nothing to operate: Pinecone and turbopuffer.
Yes. For vector database, Pinecone, Qdrant, Weaviate, Chroma, pgvector, LanceDB and 3 more have a free tier a small product can start on.
Yes. For vector database: Qdrant, Weaviate, Chroma, pgvector, LanceDB, MongoDB (self-hostable) and 5 more.
At 10,000 users, the cheapest is turbopuffer at $21 a month on Launch. From each vendor's pricing page.