> For the complete documentation index, see [llms.txt](https://docs.thereportinghub.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.thereportinghub.com/bi-genius/bi-genius-required-azure-services.md).

# BI Genius Required Azure Services

Everything you need to deploy the BI Genius

BI Genius deploys two Azure services into your own Azure environment, alongside your existing Reporting Hub app.

{% hint style="info" %}
BI Genius **reuses your existing Reporting Hub Azure App Service;** no additional App Service, SQL Database, capacity, or Translator is required.
{% endhint %}

### Services BI Genius Deploys

| Service                                                                                                                                | Purpose                                                                                                                            | Recommended starting point                                                       |
| -------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------- |
| **Azure Database for** [**PostgreSQL flexible server**](https://azure.microsoft.com/en-us/pricing/details/postgresql/flexible-server/) | Stores BI Genius configuration, agents, and query history.                                                                         | **Standard\_B1ms** tier, **32 GiB** storage. Scale up later in the Azure portal. |
| **Azure AI Foundry (**[**Azure OpenAI**](https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/)**)**    | Hosts the AI models that power BI Genius agents. Deployed to your own tenant, so your data and inference stay in your environment. | The three default models below. Add or change models any time.                   |

### AI Models and Token Costs

Because BI Genius runs on **Azure AI Foundry in your own tenant, it does not restrict which AI models you can use.** The installer deploys a working set of models by default, and you can deploy and select any other model available in Azure AI Foundry afterward.

**Deployed by default:**

<table><thead><tr><th width="224">Model</th><th>Used for</th></tr></thead><tbody><tr><td><strong>GPT (latest)</strong></td><td>The primary chat/reasoning model behind agent answers.</td></tr><tr><td><strong>GPT mini</strong></td><td>A smaller, lower-cost model for lighter or faster requests.</td></tr><tr><td><strong>text-embedding-3-small</strong></td><td>Generates embeddings for semantic search and matching.</td></tr></tbody></table>

After installation, you can deploy additional models in Azure AI Foundry and choose which ones an agent uses from **BI Genius AI Settings**. See AI Settings to select models, and Token Limits in Azure to manage rate limits.

#### How token costs work

The models run in **your own Azure subscription**, so token usage is billed **directly by Azure at Azure OpenAI pricing** for whichever models you deploy. **Reporting Hub does not add any token charge.** Rates are pay-as-you-go and vary by model (input and output tokens are priced separately; embedding models are priced per token).

For current, per-model rates:

* [Azure OpenAI Service pricing](https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/)
* [Azure pricing calculator](https://azure.microsoft.com/en-us/pricing/calculator/) — estimate cost based on your expected model and token volume.

{% hint style="info" %}
Because you own the Azure AI Foundry resource, you have full visibility and control over model choice and spend.
{% endhint %}

### Key Points

The installer automatically configures both required resources. These services deploy to your own Azure environment rather than Reporting Hub's infrastructure, **and all Azure subscription fees, including AI token usage, are the responsibility of your organization.**

Your Reporting Hub app must be version **7.7.0 or higher** to deploy BI Genius.


---

# 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://docs.thereportinghub.com/bi-genius/bi-genius-required-azure-services.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.