Cloud provider services - verified
Azure AI Search (vector search)
Azure AI Search is listed under cloud provider services (deployment type: managed provisioned). First listed price, in its own unit: $0 / $73.73 / $245.28 / $981.12 / $1,962.24 / $2,802.47 / $5,604.21, per search unit per month (Free, Basic, S1, S2, S3, L1, L2; as displayed with the page default region and currency). Max dimensions: 4,096. Stated: hybrid and sparse search and built-in embedding. Read from the vendor's own pages on October 18, 2026.
Read from learn.microsoft.com, azure.microsoft.com. Docs - Pricing - Compare every vector database
Status
- Availability label
- Not stated
No GA or preview label for vector search is quoted from the pages checked.
- Renamed on pricing page
Azure AI Search is shown as Foundry IQ (Azure AI Search)
The Azure pricing page presents the service as Foundry IQ (Azure AI Search). The vector search docs we read still call it Azure AI Search.
“Foundry IQ (Azure AI Search)”
azure.microsoft.com “Azure AI Search defines hybrid search as the execution of vector search and keyword search in the same request.”
learn.microsoft.com
How Azure AI Search charges
Every price Azure AI Search states, in its own unit, with the quote and where it comes from. Nothing is converted.
| Price | Unit, as stated | Quote and source | Where it comes from |
|---|---|---|---|
| Per search unit per month | |||
| $0 / $73.73 / $245.28 / $981.12 / $1,962.24 / $2,802.47 / $5,604.21 | per search unit per month (Free, Basic, S1, S2, S3, L1, L2; as displayed with the page default region and currency) | “Price per SU (Search unit) $0/month $73.73/month $245.28/month $981.12/month $1,962.24/month $2,802.47/month $5,604.21/month” |
|
Free tier and limits
- Free tier
Free tier at $0/month per search unit
“Price per SU (Search unit) $0/month”
azure.microsoft.com - Limits
- Not stated
The limits page gives vector index size limits per tier and region rather than one figure, so no single limit is listed here.
Search and indexing
- Max dimensions
4,096
“Maximum dimensions per vector field 4096”
learn.microsoft.com - Distance metrics
cosine, dotProduct, euclidean
“cosine This metric measures the angle between two vectors and isn't affected by differing vector lengths.”
learn.microsoft.com “dotProduct This metric measures both the length of each pair of two vectors and the angle between them.”
learn.microsoft.com “euclidean (also known as l2 norm) This metric measures the length of the vector difference between two vectors.”
learn.microsoft.com - Index types
Exhaustive KNN, HNSW
“Exhaustive K-Nearest Neighbors (KNN), which performs a brute-force scan of the entire vector space. - Hierarchical Navigable Small World (HNSW), which performs an Approximate Nearest Neighbor (ANN) search.”
learn.microsoft.com - Hybrid and sparse search
Yes: vector plus keyword search, fused with RRF
“Azure AI Search defines hybrid search as the execution of vector search and keyword search in the same request.”
learn.microsoft.com “if you do a hybrid search that combines vector and text queries in the same request, Reciprocal Rank Fusion (RRF) is used for scoring the final search results.”
learn.microsoft.com - Metadata filtering
Yes
“A query request can include a vector query and a filter expression.”
learn.microsoft.com - Multi-tenancy
- Not stated
Not described on the pages checked.
Built-in embedding and reranking
- Built-in embedding
Yes: integrated vectorization via indexer pipelines calling a configured model endpoint
“For internal processing, Azure AI Search offers integrated data chunking and vectorization in an indexer pipeline.”
learn.microsoft.com - Built-in reranking
- Not stated
A semantic ranker is listed as an add-on on the pricing page, which does not describe what it does, so it is not listed here as built-in reranking.
Deployment, license and SDKs
- Regions and clouds
- Not stated
Azure only; no region list appears in the text of the pages checked.
- BYOC and self-host
- Not stated
Managed Azure service; not applicable.
- License
- Not stated
Managed service; no license stated.
- SDKs
- Not stated
Not listed on the pages checked.
Vendor-stated claims
Performance, scale and SLA figures as Azure AI Search states them. Not measured.
No performance, scale or SLA figure is recorded from the pages checked.
Research notes
The Azure pricing page now presents the service as "Foundry IQ (Azure AI Search)". Prices are per search unit (SU), billed by replicas x partitions; the displayed figures depend on the region and currency selected on the page.
FAQ
How much does Azure AI Search cost?
In Azure AI Search's own units: $0 / $73.73 / $245.28 / $981.12 / $1,962.24 / $2,802.47 / $5,604.21 (per search unit per month (Free, Basic, S1, S2, S3, L1, L2; as displayed with the page default region and currency)). As of October 18, 2026; prices are not converted.
What is the maximum vector dimension in Azure AI Search?
4,096, per the vendor: "Maximum dimensions per vector field 4096"
Does Azure AI Search support hybrid search?
Yes: vector plus keyword search, fused with RRF, per the vendor: "Azure AI Search defines hybrid search as the execution of vector search and keyword search in the same request."
Does Azure AI Search have built-in embedding or reranking?
Embedding: Yes: integrated vectorization via indexer pipelines calling a configured model endpoint. Reranking: not stated. A semantic ranker is listed as an add-on on the pricing page, which does not describe what it does, so it is not listed here as built-in reranking.
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.