Notebookcheck Logo

Microsoft expands Foundry model router at Ignite 2026 as costs climb

The Microsoft Ignite 2026 official branding.
ⓘ Microsoft.com
The Microsoft Ignite 2026 official branding.
Microsoft expanded its Foundry model router at Ignite 2026 with a pool of the top 50 models, as Gartner warns agentic AI inference costs may rise fivefold by 2028.

Microsoft is putting model routing at the center of its pitch to enterprises worried about AI bills. At Ignite 2026, which opened in San Francisco on November 17, the company announced an expanded model router for Microsoft Foundry, its AI development platform formerly known as Azure AI Foundry.

The timing reflects a wider cost problem. In August, Gartner predicted that AI inference costs per agentic workflow will increase more than fivefold through 2028, even as per-token prices fall. The firm says routing a task to an agentic reasoning model raises inference costs by at least five times compared with a basic chatbot interaction. As one way to keep spending in check, it recommends inference tiering, which sends simpler requests to cheaper models.

What changes with the model router

The model router is not new. Microsoft made it generally available at Ignite 2025, and it already works as a single deployment that assesses each prompt and passes it to a suitable underlying model. According to the Ignite 2026 Book of News, the router will now draw on an expanded pool featuring the top 50 models in Foundry, work with AI Gateway, and support more Messages and Responses APIs. Microsoft says this lets customers balance quality, cost, and performance without choosing models manually. The company has not given an availability date for the expanded pool.

Customers can pick from three routing modes. Balanced is the default and selects the most cost-effective model within a narrow quality range of the best option for each prompt. Cost mode widens that range, with Microsoft’s documentation citing roughly 5 to 6 percent as an example, while Quality mode always picks the top-rated model regardless of price. Microsoft has not published an average savings figure for the router, and the router itself bills input prompts at its own listed rate.

Decision-1.1 and new cost controls

Microsoft also made Microsoft-Decision-1.1 generally available. The model is built to handle decisions in software at scale, and Microsoft CEO Satya Nadella said the company uses it internally for routing, data labeling, personalization, and content filtering. Microsoft says it is more than twice as fast as the first version at the same price. It is available in Foundry, OpenRouter, and Vercel.

On the spending side, Agent 365 Cost Management is now in preview, giving admins a central view of usage-based AI services along with spending policies, limits, and alerts.

Google LogoAdd as a preferred source on Google
Mail Logo
static version load dynamic
Loading Comments
> Expert reviews and news on laptops, smartphones and tech innovations > News > News Archive > Newsarchive 2026 11 > Microsoft expands Foundry model router at Ignite 2026 as costs climb
Darryl Linington, 2026-11-18 (Update: 2026-11-18)