Skip to main content
This article provides a summary of the latest releases and major documentation updates for Azure model router, including new supported models, routing features, and deployment options.

​
May 2026

​
Seven new models added

Model router now supports 28 models. Version 2025-11-18 adds support for seven new models: gpt-5.4, gpt-5.4-mini, gpt-5.4-nano, gpt-5.3-chat, gpt-5.5, claude-opus-4-7, and grok-4.1-fast-reasoning. To use claude-opus-4-7 in your model router deployment, you need to first deploy it to your Foundry resource (see Deploy and use Claude models). grok-4.1-fast-reasoning model router support is in preview.

​
Increased quota limits

Model router quota limits increased across Tier 1 through Tier 6 for both GlobalStandard and DataZoneStandard deployment types. For the updated limits, see Quotas and limits.

​
March 2026

​
Four new models added

Version 2025-11-18 of model router adds support for four new models: gpt-5.2, gpt-5.2-chat, Deepseek-v3.2, and claude-opus-4-6. To use claude-opus-4-6 in your model router deployment, you need to first deploy it to your Foundry resource (see Deploy and use Claude models). Deepseek-v3.2 and claude-opus-4-6 model router support is in preview.

​
Automatic failover

Model router now includes built-in automatic failover. When a routed model experiences endpoint instability, model router transparently redirects the request to the next most appropriate model, so transient issues with any single model don’t disrupt your application. Failover is enabled for default model router deployments — no additional configuration is required. For more information on the failover feature and how it works with routing mode and model subsets, see the Model router concepts guide.

​
November 2025

​
Anthropic models added

Version 2025-11-18 of model router adds support for three Anthropic models: claude-haiku-4-5, claude-opus-4-1, and claude-sonnet-4-5. To include these in your model router deployment, you need to first deploy them yourself to your Foundry resource (see Deploy and use Claude models).

​
Model router GA version

A new model router model is now available. Version 2025-11-18 includes support for all underlying models in previous versions, as well as 10 new language models. It also includes new features that make it more versatile and effective.
  • Routing profiles let you skew model router’s choices to optimize for quality or cost while maintaining a baseline level of performance.
  • Model router supports custom subsets: you can specify which underlying models to include in routing decisions. This gives you more control over cost, compliance, and performance characteristics.
  • Model router supports Global Standard and Data Zone Standard deployment types.
For more information on model router and its capabilities, see the Model router concepts guide.

​
August 2025

​
New version of model router (preview)

  • Model router now supports GPT-5 series models.
  • Model router for Microsoft Foundry is a deployable AI chat model that automatically selects the best underlying chat model to respond to a given prompt. For more information on how model router works and its advantages and limitations, see the Model router concepts guide. To use model router with the Completions API, follow the How-to guide.

​
May 2025

​
Model router (preview)

Model router for Foundry is a deployable AI chat model that automatically selects the best underlying chat model to respond to a given prompt. For more information on how model router works and its advantages and limitations, see the Model router concepts guide. To use model router with the Completions API, follow the How-to guide.