Vector databases · Weaviate B.V.

Weaviate

Open-source vector database with built-in hybrid (vector + keyword) search, available self-hosted or as managed cloud.

Visit Weaviate Alternatives

Weaviate is an open-source vector database that stores objects and their vector embeddings together, supporting pure vector similarity search, keyword (BM25) search, and hybrid search that combines both in a single query. It has a native module system for generating embeddings from popular providers (OpenAI, Cohere, Hugging Face) directly during ingestion or query time, and supports GraphQL and REST APIs alongside client libraries in major languages. Weaviate can be self-hosted via Docker or Kubernetes, giving full control over infrastructure, or consumed through Weaviate Cloud, the managed offering with serverless and dedicated-cluster tiers billed monthly or via prepaid contracts. It is commonly used for RAG applications, recommendation engines, and search products needing both semantic and exact-match retrieval in one system.

At a glance

Vendor Weaviate B.V.
Pricing model Free tier + paid plans
Free tier Yes
Deployment Cloud, Self-hosted
Open source Yes (BSD-3-Clause)
Best for Teams wanting hybrid semantic + keyword search with the flexibility to self-host or go managed.

Pricing

Self-hosted is free; Weaviate Cloud has a free tier, a pay-as-you-go Flex plan, and prepaid Premium plans for shared or dedicated deployments.

Plan Price Notes
Free $0/month 100,000 objects, 1GB memory, 10GB disk, 1 collection
Flex From $45/month Pay-as-you-go, shared cloud cluster, 99.5% uptime SLA
Premium (Shared/Dedicated) From $400/month Prepaid contract, up to 99.95% uptime, shared or dedicated deployment

Prices read from the vendor's own page on September 21, 2026. Vendors change prices; check the source before you budget.

Features

  • Native hybrid search (vector + BM25 keyword)
  • Built-in embedding generation modules
  • GraphQL and REST query APIs
  • Self-hosted (Docker/Kubernetes) or managed cloud deployment
  • Multi-tenancy for SaaS applications
  • Generative search (RAG) module integration

Integrations

Profile last reviewed September 21, 2026

Head to head

Alternatives

Pinecone Fully managed, cloud-only vector database for similarity search and retrieval-augmented generation at scale. Qdrant Open-source vector database written in Rust, focused on filtered similarity search with a free managed cloud tier. Milvus Open-source vector database built for billion-scale similarity search, governed under the Linux Foundation. Chroma Open-source embedding database designed for simple local-first development, with a managed serverless cloud tier.

Weaviate in the index now

Terms to know

Machine learning Building models that learn patterns from data to make predictions or decisions, rather than following hand-coded rules. Vector database A database optimized to store numeric embeddings and quickly find the ones most similar to a given query vector.

Related guides

How to choose a vector database Pick a vector database by deployment model, scale and search type, not by benchmark charts — most teams' real constraint is who runs the cluster.