When Microsoft started to deploy AI models in what is now its Foundry platform, it was building on its partnership with OpenAI. OpenAI was able to use Azure infrastructure to train its models, and in return, Microsoft became the first commercial partner to use them.
Azure OpenAI has been a successful product for both businesses. But as more organizations got access to OpenAI models, Microsoft’s stable of models grew to include not only OpenAI’s, but also models from Anthropic and Hugging Face, as well as models from Meta, Mistral, and DeepSeek. At the same time, Microsoft has continued to offer its own Cognitive Services models for computer vision and text processing, as well as the Phi series of efficient lightweight models for use on the edge.
With access to more than 11,000 different models, Foundry has proven to be a useful way to build modern AI-based applications, offering many agent-focused features, including tools to ground models using Microsoft’s graph-based IQ data sources. But one key element has been missing — Microsoft’s own large-scale frontier models.
Microsoft AI has a long history
It’s not that Microsoft is new to developing its own AI models. Microsoft Research has been a hub for deep learning for much of the last decade, with models that regularly top benchmark tables. But it hasn’t taken the same general-purpose approach as Anthropic, OpenAI, or even Google, instead producing more focused models.
Now Microsoft has begun to roll out its own foundation models as part of its Microsoft AI (MAI) program. With a focus on offering lower token cost than competitors, MAI has spotted a gap in the market. It’s a sensible move to make, too. The days of free and low-cost tokens have gone, never to return, as hyperscale vendors look to recoup the massive multi-billion-dollar investments they’ve made in AI data centers.
So-called “tokenmaxxing” is no longer economically viable, dumping massive data sets into LLMs with the hope of getting results. Instead, inference needs to be done at a lower cost, using models to help choose models and dedicated hardware that can process tokens for fewer watts and less heat. With that philosophy at the heart of its design, MAI describes its approach as “humanist”, with a focus on safety and environmental impact.
MAI models may not have the reach of the more popular general models from Anthropic or OpenAI, but the different models provide support for common scenarios, from cybersecurity, to coding, to transcription. As part of its MAI offering, Microsoft provides a tuning service that allows you to use your own data to build custom versions of the models.
Using Microsoft AI models
While most of the MAI models are available through Azure’s Foundry service, two are reserved for other applications. Currently MAI-Cyber-1.1-Flash is used as part of Microsoft’s MDASH security system, and MAI-Code-1.1-Flash is used as part of the GitHub Copilot service.
The most complex AI applications can use MAI’s Thinking model, MAI-Thinking-1. Microsoft notes that, like other MAI models, MAI-Thinking-1 runs with a much smaller footprint than competing models but still delivers the results users are expecting. Certainly, published benchmarks show good results — and Microsoft isn’t afraid of publishing numbers that favor some of the bigger models from Anthropic and OpenAI.
The key for Microsoft is to show that it gets satisfactory results at a lower cost. The aim is not to exhaust token budgets, but to gain market share by showing that you can get results that are nearly as good, for a much lower cost. There’s little downside to switching to using the new MAI models, as they can be called using the existing Foundry Azure OpenAI APIs. If you’ve got existing code, start by deploying MAI-Thinking-1 to your Foundry instance, then change your API call to the model’s endpoint URL and start sending messages to the deployed model. You can set a limit on the number of tokens used to complete a request, helping manage your application budget.
MAI-Thinking-1 can use tools via function calls, so you can build it into your own agents. More complex operations can take advantage of its ability to save encrypted reasoning chains from request to request, allowing you to quickly move to the next response in a chain, refining data to produce new prompts as your agent runs.
Like other large models, MAI-Thinking-1 can stream chunks of data back to your code instead of delivering a complete chat object. This can help with user experience, letting users see progress rather than being left waiting for a response with no cues. Of course, if you’re using MAI-Thinking-1 in a long-running workflow, there’s no need to stream data, as you’re passing responses through a chain of requests, possibly using Microsoft’s new decision-scoring model as part of an agent router to determine which steps are chosen and which models each step uses.
Shrinking AI with
[…]
Content was trimmed to protect the source. Please visit the original article for the full text.
Read the original article: