Choosing the right vector database is critical for any AI product that must ground responses in private data—customer records, team documentation, internal metrics, and more. The best choice ensures that your AI can quickly find accurate information using retrieval-augmented generation (RAG), while scaling seamlessly and staying affordable. In this guide we'll be comparing the best vector databases available in 2025: [Turbopuffer](#turbopuffer), [Pinecone](#pinecone), [Qdrant](#qdrant), [pgvector](#pgvector), [Cloudflare Vectorize](#cloudflare-vectorize), [Weaviate](#weaviate), [Milvus/Zilliz](#milvus-zilliz), [Turso Vector](#sqlite-vec-and-turso-vector), [MongoDB Atlas Vector Search](#mongodb-atlas-vector-search), [Chroma](#chroma), and [Redis](#redis). ## Introduction When we set out to launch [AI Copilots](/ai-copilots), our customizable AI chat product for React, we faced the challenge of selecting a vector database firsthand. Because our product manages the entire conversation loop, including message persistence for each user, we needed a vector database that could serve proprietary knowledge with multi-tenant isolation, real-time streaming, scalability, and cost-effectiveness. It’s a crowded market with many competing solutions, so we spent months testing different approaches. In the end, we chose a hybrid approach where we run both BM25 (keyword/semantic) and vector similarity searches, optionally followed by a rerank step. In this post we'll outline the criteria we used and the tradeoffs we found, so you can pick the best vector database for your AI in 2025. ## High-level considerations During our research, we discovered that vector databases vary greatly in terms of features, limitations, and performance. Comparing benchmark speeds alone isn't enough, and a number of factors helped us make the right decision: - **Performance & scalability**: Performance is crucial for us, as we need to provide responsive AI agents for our customers. While we weren't able to benchmark every solution, we'll discuss available third-party benchmarks. - **Features**: We focused on indexing strategies, namespace support, which give us the ability to split data by type and tenant. We also quickly identified that hybrid search is essential for robust RAG solutions, and because our agents run close to the user on edge runtimes, an HTTP API or edge-compatible SDK was a must. - **Limitations**: Each option varies greatly in terms of limitations, particularly when it comes to indexes and namespaces. - **Enterprise compatibility**: As with other enterprise service providers, compliance and security are key. HIPAA, SOC2, single sign-on, and similar enterprise features are non-negotiable requirements. - **Cost**: As a provider, cost of goods directly affects what we pass on to customers, so pricing is a major factor—especially for systems with large data ceilings. For consistency we've compared providers with a standard formula\*. - **Extension vs dedicated database**: Building a vector search solution into your existing database (e.g. Postgres) can be tempting, as it will simplify looking up data, but may lead to resource contention and scalability issues if not planned well. Using a separate, dedicated, vector database avoids these issues, but requires ongoing data synchronization between sources.

\* 1536 dimensions, 1 million reads, 1 million writes, and 10 namespaces (where supported).

--- ## Turbopuffer (our pick) [#turbopuffer] } name="Turbopuffer" url="https://turbopuffer.com" /> Thanks to its performance, low cost, [crazy high limits](https://turbopuffer.com/docs/limits), and enterprise features without enterprise costs, Turbopuffer became the obvious choice for us when building [AI Copilots](/ai-copilots). We experienced firsthand the reason why they're the choice of some of our favorite tools like Cursor, Notion, and Linear. ### Features Turbopuffer supports both vector and BM25 indexes, making it a great fit for both search and RAG use cases. It's serverless, and you only pay for what you use: storage, writes, and queries. You can pre-warm a namespace via API, which ensures our Copilots respond instantly. Multi-tenancy is simple and scalable. Each customer and project gets its own namespace, and there are no hard limits. Since performance can degrade as vector stores grow, isolating tenants like this actually improves performance. SDKs are available in TypeScript, Python, and Go, and when we ran into an issue with the TypeScript client, their team fixed it in hours. Turbopuffer also includes enterprise-grade compliance features like HIPAA BAA, SOC 2, and CMEK, even on the non-enterprise plan. Enterprise plans allow you to BYOC (bring your own cloud) and native multi-tenant support. One of the most compelling reasons to use Turbopuffer is its cost. It came in an order of magnitude cheaper than some other solutions, even when considering open source self hosted solutions. Using the standard pricing test, the cost comes in at under $10/month, with a minimum spend of $64/month. Their pricing calculator is clear and predictable, with no hidden fees. ### Drawbacks - Not open source. - A small learning curve to get the [best performance](https://turbopuffer.com/docs/performance). - Serverless means there's an initial latency, but can be avoided with pre-warming API call. - No free tier with $64/month minimum spend. - No built-in embedding support, bring your own embedding model. --- ## Pinecone [#pinecone] } name="Pinecone" url="https://pinecone.io" /> [Pinecone](https://pinecone.io) is one of the best-known managed vector DBs. ### Features Pinecone supports vector similarity search with metadata filtering and offers built-in embeddings at an extra cost. It's available on AWS, GCP, and Azure, and scales to billions of vectors with solid reliability. Pinecone's limits include up to 100k namespaces in their standard plan but only 20 indexes, with higher limits available on enterprise plans. Pinecone pricing can be confusing as there are many different options such as pods-based pricing, serverless pricing, and extra add-ons for rerank, embedding, support, and "assistant" features. There is a [pricing calculator](https://www.pinecone.io/pricing/estimate/) available to help you estimate cost. Based on our standard pricing test, the total cost comes in at $41. They do offer a free tier and paid plans start at $50/month minimum usage. Pinecone's built-in inference covers embedding and re-ranking. We found the available embedding models somewhat limiting and would prefer to use an external embedding model anyway. ### Drawbacks - 20 index limit unless on enterprise. - Overwhelming pricing options. - Hybrid search isn't as seamless outside Python. --- ## Qdrant [#qdrant] } name="Qdrant" url="https://qdrant.io" /> [Qdrant](https://qdrant.io) is a fast, open-source vector database written in Rust. ### Features Qdrant supports filtering, clustering, and hybrid scoring, and works well with high-cardinality metadata. You can self-host via Docker or Kubernetes, or use their managed service. The API is well-documented, with SDKs in [several languages](https://qdrant.tech/documentation/interfaces/), including rust which is somewhat rare. [Multi-tenancy](https://qdrant.tech/articles/multitenancy/) is extremely flexible with a multitude of sharding options. Their cloud pricing is based on storage and compute use, with a small free tier available. A [pricing calculator](https://cloud.qdrant.io/calculator) is available, and based on our standard test the price is $102 on AWS us-east without quantization, which can reduce memory usage. With disk caching and quantization turned on, this can be reduced to $27. ### Drawbacks - Manual sharding required. - No built-in embedding generation. - Slightly steeper learning curve than Pinecone or Turbopuffer. --- ## pgvector [#pgvector] } name="pgvector" url="https://github.com/pgvector/pgvector" /> [pgvector](https://github.com/pgvector/pgvector) is a Postgres extension that lets you store and query vectors alongside relational data. ### Features pgvector is ideal for teams already using Postgres that want to unify structured data with vector search. You get full SQL support, transactional guarantees, and the benefits of a mature ecosystem. It's open source and free to use. Costs come down to whatever infrastructure you're running Postgres on. For teams already running Postgres in production, this is a low-friction entry point, although studying the different indexing options will be prudent. Managing a vector database on pgvector is not as easy as a dedicated option that's targeted specifically for vector search. It also comes preinstalled on many popular vendors such as [Supabase](https://supabase.com/docs/guides/database/extensions/pgvector), [AWS](https://aws.amazon.com/blogs/database/leverage-pgvector-and-amazon-aurora-postgresql-for-natural-language-processing-chatbots-and-sentiment-analysis/), and [Neon](https://neon.com/docs/extensions/pgvector). While pgvector can be a great choice if you're already familiar and comfortable with Postgres, you should be aware of some risks. Having a vector database that lives next to your main content is very convenient, but vector indexes can use a lot of memory and performance and costs of your database can be negatively affected. Based on your usage scenario, you also must pick between IVFFlat and HNSW, which is a tradeoff between querying performance and memory usage. To model your data efficiently, you may want to use [partitioning](https://www.postgresql.org/docs/current/ddl-partitioning.html) to reduce the size of your indexes, especially in a multi-tenant situation. If you're using an ORM, such as Prisma, as of September 2025, they still don't fully support [pgvector](https://github.com/prisma/prisma/issues/26546) and [partitioning](https://github.com/prisma/prisma/issues/1708) without workarounds. ### Drawbacks - Can be slower than dedicated vector DBs at high scale. - Requires Postgres tuning and expertise for best performance. - Many popular ORMs lack support for pgvector and partitioning. --- ## Cloudflare Vectorize [#cloudflare-vectorize] } name="Cloudflare Vectorize" url="https://developers.cloudflare.com/vectorize" /> [Cloudflare Vectorize](https://developers.cloudflare.com/vectorize) is a vector database that is part of Cloudflare's Workers AI platform, designed for edge-native workloads. ### Features Vectorize supports 50k namespaces and indexes per account and up to 5M vectors per index. The serverless model makes it easy to use and it integrates well with other Cloudflare products. It's one of the easiest solutions to get up and started with if you're already on the Workers platform. Vectorize does not yet appear in the [compatibility](https://developers.cloudflare.com/data-localization/compatibility/) matrix for their data location suite which can make data residency compliance difficult or impossible. Cloudflare also offers an auto-RAG feature built on top of vectorize, R2, and workflows which can work great for simple implementations but we found it to be a little slow and it's difficult to integrate from a SaaS provider perspective where we need to communicate indexing status to a multi-tenant dashboard. Vectorize has an HTTP API but the native SDK is only available inside workers itself. Unfortunately Cloudflare does not support full text indexes and only a limited amount metadata (attributes). This makes a hybrid approach very difficult as you'd need a different database for FTS. Pricing is usage-based and for our standard test of 1 million documents with 1 million reads and 1 million writes, the cost is $47. Embeddings can be generated manually or by using Cloudflare's AI models. ### Drawbacks - Many limits such as metadata limits and 5M vector limit per index (you'll need to shard). - Regional data compliance is unclear. - Not open source. - No full-text-search means no hybrid searches. --- ## Weaviate [#weaviate] } name="Weaviate" url="https://weaviate.io" /> [Weaviate](https://weaviate.io) is an open-source vector database, and of the first to market, meaning they have a very deep feature set. ### Features Weaviate provides semantic search, hybrid scoring, gRPC, and GraphQL support. It supports multi-modal inputs (text, image, video) and offers built-in embedding options provided by third party integrations. You can self-host or use their cloud service. Weaviate has two pricing models, a classic cloud deployable model where you pay for "AIU"s and a more transparent serverless pricing model. Serverless [pricing](https://weaviate.io/pricing/serverless) is usage based on stored vector dimensions and query usage, with a starting plan around $25/month. Our test of 1536 dimensions with 1 million reads and writes works out to $153 but if you choose the less performant compression version, it's only $25. ### Drawbacks - gRPC and GraphQL API has a learning curve. - Relatively high cost compared to other solutions. - Complicated pricing. --- ## Milvus/Zilliz [#milvus-zilliz] } name="Milvus/Zilliz" url="https://milvus.io" /> [Milvus](https://milvus.io) is a highly scalable, open-source vector database built for billions of vectors. The hosted/managed version of Milvus is called Zilliz. ### Features Milvus supports distributed deployments on Kubernetes and includes more indexing strategies than any other competitor we could find such as IVF, HNSW, and DiskANN. It's best suited for enterprise-scale use cases where infrastructure is not a bottleneck. Costs come down to your infrastructure and operations complexity. Milvus uses collections rather than namespaces. Zilliz has a [pricing calculator](https://zilliz.com/pricing#calculator). Pricing for serverless 1536 dimension vector with 1 million reads and 1 million writes is $89. There is also a dedicated version which estimates a cost of $114. They also offer a free plan with up to 5gb of storage. Zilliz has SOC2 compliance and available SLAs. ### Drawbacks - Setup and scaling complexity. - More expensive compared to other options. --- ## sqlite-vec and Turso Vector [#sqlite-vec-and-turso-vector] } name="Turso Vector" url="https://turso.tech" /> SQLite is the world's most deployed database because it's fast and embeddable. sqlite-vec is an extension to SQLite and also the successor to sqlite-vss, an earlier and less performant solution by the same author. Sqlite-vec is particularly appealing in situations where each customer or user has their very own database instance leading to nearly unlimited horizontal scalability. If you'd rather not deal with the infrastructure behind using SQLite in the cloud, [Turso.tech](https://turso.tech) offers their own hosted sqlite solution with built-in vector support. ### Features Turso's solution has no extension to install and the API is easy as it's just a type of database. However, it's important to note that the libSql version is not the same as sqlite-vec, so you won't be able to migrate between the two. If you want to accomplish a hybrid search with both full text search and vector search, you'll need a separate full text search extension such as FTS5, which also comes preloaded when using Turso. Rather than using namespaces, you can use a separate database for each client to achieve true multi-tenancy or even per-user tenancy. With Turso, reads are also done from local replicas which makes latency extremely low. Turso has extremely low pricing including a free tier and up to 25 million queries for only $5/month. Enterprise features such as SOC2 and HIPAA will bump to their enterprise plan which starts around $400/month. If you're running sqlite in embedded manner, the performance will be limited to what hardware is available on the client. This may be fine for local chat memory or limited documentation, but this won't scale to millions of documents. ### Drawbacks - Won't handle massive single databases, but an excellent choice for horizontal scaling. - Won't run natively on many edge networks without an HTTP remote client as offered by [libSql remote protocol](https://docs.turso.tech/sdk/http/reference). --- ## MongoDB Atlas Vector Search [#mongodb-atlas-vector-search] } name="MongoDB Atlas Vector Search" url="https://www.mongodb.com/products/platform/atlas-vector-search" /> If you're already a Mongo user, then this may be an attractive solution to keep your stack simple. ### Features Much like pgvector and sqlite-vec, MongoDB's solution exists within a database you may already be familiar with. As with those solutions, be prepared for increased memory usage for vector indexes. Pricing is difficult to calculate with atlas as their calculator does not have vector specific pricing and it's usage based on instance size. MongoDB does have a free community edition under the [Server Side Public License](https://www.mongodb.com/legal/licensing/server-side-public-license). MongoDB has many options for clients, supports [hybrid searching](https://www.mongodb.com/docs/atlas/atlas-vector-search/hybrid-search/), and is only limited by scaling strategy and hardware. --- ## Chroma [#chroma] } name="Chroma" url="https://www.trychroma.com" /> [Chroma](https://www.trychroma.com) is an open-source serverless database that bills itself as the "retrieval database for AI". ### Features Chroma has full-text, metadata, and vector search available. Rather than namespaces, it uses collections and above that is databases and tenants. Interestingly, internally Chroma uses [sqlite](https://cookbook.chromadb.dev/core/concepts/#distance-function) and object storage much of its functionality. Chroma has many SDK clients as well as an HTTP API available for use with any language. Chroma's documentation is lacking in some areas, especially the open-source clients, but it's simple enough that we found getting started was no problem. Chroma's cloud offering has simple usage based pricing with a nice pricing [calculator](https://www.trychroma.com/pricing) which works out to $81 for 1536 dimension vector with 1 million writes and 1 million queries. --- ## Redis [#redis] } name="Redis" url="https://redis.io" /> [Redis](https://redis.io) 8.0 introduced a new native vector type that makes it one of the fastest in terms of raw speed. Redis also recently switched back to open-source under an AGPL license after a controversial closing which led to the success of forks such as Valkey. ### Features If you're already familiar with Redis, then it's a solid choice, but as with other solutions, you need to consider the size and shape of documents you wish to store. Redis achieves its performance by keeping everything in memory, and while this is super fast, it also means you need the hardware to support it. It can also use SSD, but it will suffer some performance loss. Redis offers up to 30mb for free and 1gb for $5/month. They also have flexible options for hosting on AWS, Azure, and GCP. --- ## Summary table Provider Open-source Built-in embeddings Max namespaces/indexes Max vectors per index Self-host Cost per 1536 dimension vector, 1M reads, 1M writes Turbopuffer No No No hard limit No hard limit No $9.36 Pinecone No Yes 100k namespaces / 20 indexes ~Unlimited* No $41 Qdrant Yes No No enforced limit No enforced limit Yes $102* pgvector Yes No Based on Postgres infra Based on infra Yes N/A Cloudflare Vectorize No Yes 50k namespaces 5M vectors No $47 Weaviate Yes Yes Based on infra Based on infra Yes $153.78* Milvus/Zilliz Yes No Based on cluster config – Yes $89.55 sqlite-vec / Turso Yes No N/A – – $4.99 Chroma Yes No Unlimited – Yes $81 Mongo Atlas Yes No Based on infra Based on infra Yes-ish N/A Redis Yes No Based on infra Based on infra Yes N/A