ToolsCompaniesAbout

Azure AI Search

by Microsoft@microsoftRedmond, Washington, USANo ratings yet

Microsoft's retrieval and knowledge-base service for RAG apps, agents and enterprise search

Visit azure.microsoft.com
Tool type
Search and retrieval service
Made for
Developers and enterprise teams
Runs on
Azure cloud service
Managed in Azure portal and Foundry portal; 30+ regions
Last checked
28 Oct 2026
2 product sources

What it does

Azure AI Search, now branded Foundry IQ, takes in enterprise content such as Word, PowerPoint, Excel, PDF, PNG, RTF, JSON, HTML and XML files, plus data from Azure Cosmos DB, Azure SQL Database, Blob Storage, SharePoint, OneLake and the web. It produces searchable indexes and reusable knowledge bases, and returns relevant, permission-trimmed results or synthesized answers to applications and AI agents.

Developers use it to ground generative AI apps in private data. An import wizard in the Azure portal automates parsing, chunking, enrichment and embedding. Queries can combine keyword, vector and hybrid search, and agentic retrieval adds query planning, reranking and answer synthesis. A knowledge base built once can be reused across several agents. Document-level access control lists keep answers aligned with each user's permissions.

It suits developers and enterprise teams building RAG systems, agents or search engines on Azure. An Azure subscription is required, and knowledge bases also need a standard agentic retrieval plan. Costs combine capacity or serverless compute with add-ons such as agentic retrieval and semantic ranker, so estimating spend takes work. Serverless is in preview, and confidential-compute resources lack semantic ranker, agentic retrieval, skillset execution and vectorization.

What it can do

  • Hybrid search combining keyword and vector queries in one request
  • Agentic retrieval with query planning, reranking and answer synthesis
  • Reusable knowledge bases connecting multiple sources to many agents
  • Import wizard automating parsing, chunking, enrichment and embedding
  • Document-level ACL synchronization and query-time permission trimming
  • Built-in indexers for Cosmos DB, Azure SQL, Blob Storage and SQL Server on Azure VMs

Works with

  • Azure Cosmos DB
  • Azure SQL Database
  • Azure Blob Storage
  • Microsoft SharePoint
  • Microsoft OneLake
  • Azure Data Factory
  • Azure Logic Apps
  • Microsoft Foundry
  • Azure OpenAI

Example workflows

Ground an agent in SharePoint documents
Inputs: SharePoint and Blob Storage documents. Steps: add them as knowledge sources, group them into a knowledge base, attach it to an agent in the Foundry portal. Output: agent answers drawn from those sources, trimmed to each user's permissions.
Index files for a RAG app
Inputs: PDF and Office files in Azure Blob Storage. Steps: run the portal import wizard to parse, chunk, enrich and embed, then query with hybrid search. Output: a searchable index feeding a generative AI application.

Before you choose

  • Serverless pricing is labeled preview, with billing stated to begin September 13, 2026.
  • Agentic retrieval and semantic ranker are billed as add-ons on top of base service costs.
  • Confidential-compute resources cost extra and lack several features such as semantic ranker and agentic retrieval.

Listed under

Get started

Pay as you go or free trial up to 30 days

  1. Create or sign in to an Azure account and subscription.
  2. Create a search service in the Azure portal or Foundry portal, choosing Dedicated or Serverless.
  3. Add knowledge sources or run the import wizard, then build a knowledge base or index.
Create an Azure account

Plans and prices

Prices in USD

Dedicated tiers (Free, Basic, Standard S1-S3, Storage Optimized L1-L2) are billed per Search Unit; Serverless is billed per Compute Unit-hour plus indexed storage. Dollar rates were not shown in the reviewed information. Azure itself offers a $200 credit for 30 days.

Dedicated (Free to L2)Usage-basedRate varies by tier and region; see rate table.
  • Free tier: 50 MB storage, 3 indexes
  • Paid tiers priced per search unit
Serverless (preview)Usage-basedRegion-dependent rate.
  • Scales to zero when idle
  • 30 indexes and 5 services per region

Source: azure.microsoft.com/en-us/pricing/details/search, checked 28 Oct 2026. Prices can change; check before you buy.

Sources for this overview

Product pages, documentation, and pricing checked 28 Oct 2026. Each source supports part of the overview; availability and prices can change.

Ratings and reviews

No ratings for Azure AI Search yet.

Be the first to rate it

What’s changed

Free account

See what’s changed at Azure AI Search

Launches, price moves and pivots, each with a date and a source. Free with an account.

Signals

Free account

See Azure AI Search’s signals

Launch traction, hiring and release activity, tracked over time. Free with an account.

Data and security

Free account

See how Azure AI Search handles your data

Training on your files, compliance, hosting and the models behind it. Free with an account.

Compare with similar tools

Free account

Compare Azure AI Search side by side

Prices, platforms and features against similar tools, with sources. Free with an account.

Where this comes from

How we research
Company website
azure.microsoft.com: product, pricing and policy pages
YC directory mirror
Batch and company name
Web search
Confirms the official site
Social accounts
Accounts the company links, and its posts on X
Human review
Checked by a person
knowledge_base

Last checked 28 Oct 2026. Every field keeps its source and date; unknown means we couldn’t confirm it.