> For the complete documentation index, see [llms.txt](https://academy.any2info.com/any2info-academy/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://academy.any2info.com/any2info-academy/no-code-platform/ai-studio/agents/getting-started/providers/azure-ai.md).

# Azure AI

### 1. Create an Azure account

Before using Azure AI, an account and subscription must be created.

* Go to the Azure portal
* Sign in or create an account
* Ensure you have an active **Azure subscription**

```
https://portal.azure.com
```

***

### 2. Create Microsoft Foundry Project

Azure organizes AI usage through resources.

* Go to **Create resource**
* Search for **Azure OpenAI** or **Azure AI Foundry**
* Create a new resource

Configuration:

* **Resource group**: create or select one
* **Region**:
  * West Europe (recommended)
  * Sweden Central (for latest models like GPT-5.x)
* **Name**: use a clear naming convention (e.g. ai-studio-prod)

This resource contains:

* Models and deployments
* API access (endpoint + keys)
* Monitoring and usage data

***

### 3. Deploy a model

Before using Azure AI, a model must be deployed.

* Open your Azure AI resource
* Go to:

```
Models + Endpoints
```

* Create a new deployment
* Select a model (GPT-4o transcribe, GPT-5.x)

Important:

* Define a **deployment name**
* This is what you will use in Any2Info (NOT the model name but it can be the same)

<figure><img src="https://870194474-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-M_kE41Rl4pOtwKfvvQq%2Fuploads%2FNp8GUBUTeF2hEbFJYMDA%2Fimage.png?alt=media&amp;token=95a3c5b4-df0c-4f1c-9f51-7098a585e7be" alt=""><figcaption></figcaption></figure>

***

### 4. Retrieve API key and endpoint

After deploying a model, you can retrieve the required credentials.

* Open your Azure AI resource
* Go to **Models + Endpoints**
* Select your deployed model

From here, you can find:

* **API Key**

These values are required to connect Azure to the Any2Info platform.

***

### 5. Cost monitoring

There are two places where you can monitor usage and costs:

#### Model usage (per deployment)

* Open your Azure AI resource
* Go to:

```
Models + Endpoints
```

* Select your **deployment**
* Go to **Metrics**

Here you can see:

* Token usage
* Requests
* Performance metrics

<figure><img src="https://870194474-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-M_kE41Rl4pOtwKfvvQq%2Fuploads%2FekqMdb6rrJC1rvcYAD4Y%2Fimage.png?alt=media&amp;token=35e693f3-20bd-4478-9489-99e1b55eccb6" alt=""><figcaption></figcaption></figure>

#### Azure cost management

This can be in the azure portal


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://academy.any2info.com/any2info-academy/no-code-platform/ai-studio/agents/getting-started/providers/azure-ai.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.