Skip to main content
Watch: Stop Building Apps. Build Tools for AI Agents

Managed services - verified

MongoDB Vector Search (Atlas)

MongoDB Vector Search is listed under managed services (deployment type: managed provisioned). First listed price, in its own unit: $0, per hour (Atlas Free cluster). Max dimensions: 8,192. Stated: hybrid and sparse search and built-in embedding. Read from the vendor's own pages on October 18, 2026.

Read from mongodb.com. Docs - Pricing - Compare every vector database

Status

Availability label
Not stated

No GA label for vector search itself is quoted; Automated Embedding is labelled Preview (see builtInEmbedding).

How MongoDB Vector Search charges

Every price MongoDB Vector Search states, in its own unit, with the quote and where it comes from. Nothing is converted.

3 price rows in each product's own unit, grouped by unit and sorted only inside a unit
PriceUnit, as statedQuote and sourceWhere it comes from
Per cluster-hour (whole cluster, not vector-specific)
$0per hour (Atlas Free cluster)
“Free $0 /hour Free forever For learning and exploring MongoDB in a cloud environment. STORAGE 512 MB”
mongodb.com
  • Cluster priceVector search runs on Atlas clusters, so these are cluster prices, not vector-specific rates.
$0.011per hour, up to $30/month (Atlas Flex cluster)
“Flex $0.011 /hour Up to $30/month”
mongodb.com
  • Cluster priceVector search runs on Atlas clusters, so these are cluster prices, not vector-specific rates.
$0.08per hour, starts at $56.94/month (Atlas Dedicated cluster)
“Dedicated $0.08 /hour Starts at $56.94/month”
mongodb.com
  • Cluster priceVector search runs on Atlas clusters, so these are cluster prices, not vector-specific rates.

Vector search runs on Atlas clusters, so these are cluster prices, not vector-specific rates.

Free tier and limits

Free tier

Free clusters allow 3 search or vector indexes

“3 indexes (regardless of the type, search or vector) on Free clusters.”
mongodb.com
Limits

Free clusters: 3 search or vector indexes

“3 indexes (regardless of the type, search or vector) on Free clusters.”
mongodb.com

Search and indexing

Max dimensions

8,192

“You must specify a value less than or equal to 8192.”
mongodb.com
Distance metrics

euclidean, cosine, dotProduct

“euclidean - measures the distance between ends of vectors.”
mongodb.com
“cosine - measures similarity based on the angle between vectors.”
mongodb.com
“dotProduct - measures similarity like cosine, but takes into account the magnitude of the vector.”
mongodb.com
Index types

hnsw, flat

“hnsw - for graph-based index where similar vectors are connected”
mongodb.com
“flat - for flat, non-graph, index”
mongodb.com
Hybrid and sparse search

Yes: $rankFusion and $scoreFusion

“You can use $rankFusion and $scoreFusion to perform a hybrid search.”
mongodb.com
Metadata filtering

Yes (filter-type index fields for pre-filtering)

“filter - for pre-filtering documents by non-vector fields.”
mongodb.com
Multi-tenancy
Not stated

Not described on the pages checked.

Built-in embedding and reranking

Built-in embedding

Yes, Automated Embedding with Voyage AI models (Preview)

“Automated Embeddings is available as a Preview feature.”
mongodb.com
“autoEmbed type to index a text field for which you want MongoDB Vector Search to automatically generate vector embeddings using Voyage AI models.”
mongodb.com
Built-in reranking
Not stated

Not stated on the vector search type, hybrid search or overview pages checked.

Deployment, license and SDKs

Regions and clouds
Not stated

Not stated on the vector search pages checked.

BYOC and self-host

Self-managed or local deployments via the Atlas CLI

“You can also use MongoDB Vector Search with self-managed or local Atlas deployments that you create with the Atlas CLI.”
mongodb.com
License
Not stated

No license is stated on the vector search or pricing pages checked.

SDKs
Not stated

Not listed on the pages checked.

Vendor-stated claims

Performance, scale and SLA figures as MongoDB Vector Search states them. Not measured.

No performance, scale or SLA figure is recorded from the pages checked.

Research notes

The docs now call the feature "MongoDB Vector Search"; the old atlas-vector-search overview URL redirects to mongodb.com/docs/vector-search/. ANN search requires Atlas clusters on MongoDB v6.0.11, v7.0.2 or later per the overview. On the vector-search-type page the dimension limit, similarity and indexing-method text sits inside tabbed sections.

FAQ

How much does MongoDB Vector Search cost?

In MongoDB Vector Search's own units: $0 (per hour (Atlas Free cluster)); $0.011 (per hour, up to $30/month (Atlas Flex cluster)); $0.08 (per hour, starts at $56.94/month (Atlas Dedicated cluster)). As of October 18, 2026; prices are not converted.

What is the maximum vector dimension in MongoDB Vector Search?

8,192, per the vendor: "You must specify a value less than or equal to 8192."

Does MongoDB Vector Search support hybrid search?

Yes: $rankFusion and $scoreFusion, per the vendor: "You can use $rankFusion and $scoreFusion to perform a hybrid search."

Does MongoDB Vector Search have built-in embedding or reranking?

Embedding: Yes, Automated Embedding with Voyage AI models (Preview). Reranking: not stated. Not stated on the vector search type, hybrid search or overview pages checked.

Sources

Last verified from each vendor's own docs, pricing pages, READMEs and license files; every quote was string-matched against the page that day. This is a dated snapshot, not a benchmark: prices are shown in each product's own unit and change without notice, so check the linked source before you commit.

Newsletter

Know when a vector database changes its pricing

One email per week. New model releases, retrieval tooling and pricing changes and what they mean for what you build.