Microsoft has lifted the lid on the next generation of its Azure Maia custom AI chips, saying it will usher in a new phase of compute infrastructure designed for the demands of agentic inference.
The company says its Azure Maia 200, announced earlier this year, is now serving production workloads, with the successor Maia 300 planned for 2027. In a blog post, Scott Guthrie, Microsoft's executive vice president for Cloud and AI, described Maia 300 as "a complete intelligent system" built for the new types of AI workloads emerging today.
Microsoft claims a full 96-accelerator configuration will deliver up to seven times Maia 200's rack-scale token throughput, while offering 40 percent more tokens per megawatt than leading GPU-based systems. Each Maia 300 will feature eight HBM4 memory stacks providing up to 18 TB/s of peak memory bandwidth, supporting large models and long-context workloads.
The chip uses an inference-first architecture optimized for long-context, memory-intensive and decode-heavy workloads. Microsoft says Maia 300 is "built as a complete system, with software, silicon, physical rack infrastructure, networking, and datacenters co-designed to operate as a single platform."
The approach mirrors rack-scale AI equipment already developed by Nvidia for its GPU accelerators, and more recently by AMD with its Helion and Helios infrastructure, all designed to make the most of their own silicon and software stacks.
The growing emphasis on in-house integration contrasts with Microsoft's 2024 "AI Access Principles," which stressed partnerships across its technology stack. The firm previously complained to European Commission competition authorities that Google held an advantage through its integrated approach. "Only one company, Google, is vertically integrated in a manner that provides it with strength and independence at every AI layer from chips to a thriving mobile app store," Microsoft said at the time. "Everybody else must rely on partnerships to innovate and compete."
Microsoft now has its own AI chips, rack-scale designs and internally developed MAI models, giving it more control over its stack. It plans to scale Azure Maia to "multi-gigawatt deployments" starting in 2027. Guthrie said the company will share more details on its strategy at Microsoft Ignite 2026 in San Francisco next month.