analiza aiqbench
This update expands Microsoft Foundry's model router to 28 global regions while integrating newer models like GPT-5.6 and Claude Opus 4.8, automatically refreshing the available pool for default deployments without requiring redeployment. However, teams relying on configured subsets must manually add new models, as automatic updates do not apply to these restricted configurations. Crucially, swapping models alters behavioral stability—such as tool-selection logic and refusal patterns—even if the API schema remains unchanged, potentially shifting business outcomes for existing workloads.
Foundry Model Router Expands from Two Regions to 28, Refreshing Its Model Pool
Microsoft expanded Foundry's model router from two regions to 28 for global standard and 21 for data zone deployments, while adding Claude Opus 4.8 and GPT-5.6 and removing four deprecated models. Default deployments receive pool changes automatically; configured subsets exclude new models until added. The effective context window equals the smallest model in the pool. By Steef-Jan Wiggers
Microsoft recently expanded model router in Foundry Models from two regions to 28 for global standard deployments and 21 for data zone deployments, and refreshed the pool of models it selects from. Until this release, the router ran only in East US 2 and Sweden Central. The pool gained Anthropic Claude Opus 4.8 and the GPT-5.6 family, and lost gpt-5-chat, gpt-5.2-chat, gpt-5.3-chat, and DeepSeek-V3.1 as those models reached end of life. Teams on the default configuration receive the change without redeploying. Teams that configured a model subset do not. That split…
Extras afișat conform termenilor RSS ai publicației · 91 cuvinte · textul integral și figurile sunt pe site-ul publicației
