> For the complete documentation index, see [llms.txt](https://metaverse-imagen.gitbook.io/ai-tools-research/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://metaverse-imagen.gitbook.io/ai-tools-research/ai-technology/generative-ai-architectures-and-models/generative-ai-and-llms-for-text/azure-openai-microsoft.md).

# Azure OpenAI (Microsoft)

Microsoft's LLM equivalent to OpenAI is Azure OpenAI. It is a collaboration between Microsoft Azure and OpenAI, a leading research organization in artificial intelligence. Azure OpenAI offers a variety of LLM services, including:

* GPT-3, a large language model with 175 billion parameters. 
* DialoGPT, a conversational AI model that can hold natural conversations. 
* Dactyl, a model that can control physical robots.

Azure OpenAI is available through the Azure Marketplace. Developers can use it to build AI-powered applications in a variety of industries, including healthcare, finance, and customer service.

In addition to Azure OpenAI, Microsoft also has its own LLM research project called Semantic Kernel. **Semantic Kernel** is an open-source SDK that lets developers easily combine AI services like OpenAI, Azure OpenAI, and Hugging Face with conventional programming languages like C# and Python. By doing so, developers can create AI apps that combine the best of both worlds.

Here is a table that summarizes the differences between Azure OpenAI and Semantic Kernel:

<table><thead><tr><th width="138">Feature</th><th width="166">Azure OpenAI</th><th width="169">Semantic Kernel</th></tr></thead><tbody><tr><td>LLM models</td><td>GPT-3, DialoGPT, Dactyl</td><td>OpenAI, Azure OpenAI, Hugging Face</td></tr><tr><td>Programming languages</td><td>C#, Python</td><td>C#, Python</td></tr><tr><td>Availability</td><td>Azure Marketplace</td><td>Open-source</td></tr><tr><td>Cost</td><td>Pay-per-use</td><td>Free to use</td></tr></tbody></table>

Bing, Microsoft's search engine to rival Googla uses OpenAI's GPT-4 Large Language Model. GPT-4 is a 175 billion parameter model that was trained on a massive dataset of text and code. It can generate text, translate languages, write different kinds of creative content, and answer your questions in an informative way.

Bing uses GPT-4 to power a variety of features, including:

**Query Suggestions:** Bing uses GPT-4 to suggest relevant queries as you type. **Autocomplete:** Bing uses GPT-4 to complete your queries as you type. **Personalized Results:** Bing uses GPT-4 to personalize your search results based on your interests.&#x20;

GPT-4 has helped to make Bing a more powerful and personalized search engine. It is likely that Bing will continue to use GPT-4 and other LLMs in the future to improve its search results and features.