MongoDB Atlas Vector Search logo

MongoDB Atlas Vector Search

Free tier

Build intelligent applications powered by semantic search and generative AI with a native, full-featured vector database.

Free tier available·All audiences·Powered by Voyage AI·API available

Key strengths

Unified operational and vector data in a single database (no sync required)Automated Embedding with Voyage AI models managed by AtlasHybrid search combining vector, lexical, geospatial, and aggregation queriesIndependent scaling of vector search via Search NodesEnterprise-grade security and high availabilityNative reranking with Voyage AI reranker modelsAvailable on-premises via Enterprise Advanced and Community Edition
Free tier + paid plans
New York, USA
Founded 2007
Self-hostable

Facts verified against mongodb.com on

Recent changes

  • Plans updated: Free tier at $0/hour (512MB storage, shared RAM/vCPU). Flex tier at $0.011/hour (up to $30/month, 5GB storage). Dedicated tier starting at $0.08/hour ($56.94/month, 10GB–4TB storage). Atlas Infinite at $0.09/hour (public preview).
  • Models updated: Voyage AI
  • Self-hosting: now available
What's changed across AI tools →

Get alerts when MongoDB Atlas Vector Search changes

Free. We'll email you when pricing, the free tier, API access or open-source status changes.

No ratings yet

Documentation & Developer Resources

MongoDB Atlas Vector Search is accessible as a managed cloud service or self-hosted via Enterprise Advanced and Community Edition.

Integration points:

  • Voyage AI — Managed embedding generation and native reranker model support are provided through the Voyage AI integration, allowing Atlas to handle the full embedding lifecycle without external orchestration.
  • Okta — Enterprise identity and access management integration for secure, governed deployments.

Search capabilities available to developers:

  • Vector similarity search (ANN/kNN)
  • Hybrid search combining vector, lexical, geospatial, and MongoDB aggregation queries in unified pipelines
  • Native reranking via Voyage AI reranker models

Scaling architecture:

  • Search Nodes provide independent horizontal scaling of vector search workloads, decoupled from the operational database cluster.

Deployment options:

  • Fully managed: MongoDB Atlas (cloud)
  • Self-hosted: Enterprise Advanced, Community Edition

Pricing tiers for planning:

  • Free: $0/hour — 512 MB storage, shared RAM/vCPU
  • Flex: $0.011/hour — up to $30/month, 5 GB storage
  • Dedicated: from $0.08/hour — $56.94/month, 10 GB–4 TB storage
  • Atlas Infinite: $0.09/hour — currently in public preview
Alternatives

Alternatives to MongoDB Atlas Vector Search

See all alternatives
Browse all 10 vector databases tools