"Microsoft has expanded Foundry Agent Service with a wide range of AI models. LLMs from Anthropic, DeepSeek AI, Meta, Microsoft, and xAI are now available. The expanded catalog allows developers to choose the right model for their specific application. The different LLMs excel in a variety of ways, from coding to reasoning based on long inputs. Examples include DeepSeek-R1 (version 0528) and -V3 (0324), as well as variants of Grok-4."
"This brings Microsoft's AI service a step closer to the model selection of Vertex AI Agent Service, Google's counterpart to Microsoft's offering. Apart from Google's own models, which are exclusive to Google Cloud, Google offers mostly the same LLMs. The big absentee is OpenAI, which is only available from Microsoft when it comes to closed-source models. These include the latest variants (GPT-5.1) and legacy options such as o4-mini, o3, GPT-4.1, o1 and (for now) GPT-4o and GPT-4."
"Anthropic's latest models have also been added. Claude-Opus-4-1 is intended for the most complex issues. Claude-Sonnet-4-5 offers a balance between performance and multimodal workflows. Claude-Haiku-4-5 focuses on speed for interactive scenarios. General models are available for enterprise applications. Llama-4-Maverick-17B-128E-Instruct-FP8 optimizes for fast, cost-effective inferencing. OpenAI, currently not a big proponent of open-source models, does provide gpt-oss-120b via the Foundry service."
Microsoft expanded Foundry Agent Service to include LLMs from Anthropic, DeepSeek AI, Meta, Microsoft, and xAI, enabling developers to select models tailored to application needs. Model strengths range from coding to reasoning over long inputs, with examples including DeepSeek-R1 (0528), -V3 (0324), and Grok-4 variants. Anthropic additions include Claude-Opus-4-1, Claude-Sonnet-4-5, and Claude-Haiku-4-5 for complex tasks, multimodal balance, and interactive speed. Enterprise options include Llama-4-Maverick-17B-128E-Instruct-FP8 and gpt-oss-120b. The service supports streaming responses, flexible tool calling, multimodal features, grounded retrieval, and automatic model routing based on performance, accuracy, and cost. Access is via SDK, API, and Foundry Agent Playground.
Read at Techzine Global
Unable to calculate read time
Collection
[
|
...
]