Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
Aion 1.0 Plan is Microsoft's innovative local agentic reasoning framework for Windows that facilitates fully agentic workflows on devices without relying on cloud services or incurring per-token expenses. This model boasts an impressive 14 billion parameters and a context length of 32K, and it is integrated directly into Windows on compatible devices. In contrast to smaller on-device models that concentrate on basic text processing, Aion 1.0 Plan is specifically designed for local agentic reasoning, allowing applications to comprehend user intentions, utilize tools, manage files, and coordinate sub-agents directly on the device itself. It represents the latest evolution in Microsoft’s suite of on-device small language models, created for efficient local execution and signifying a shift from scalable text intelligence to more advanced local planning capabilities. Aion 1.0 Plan is a crucial component of Windows' overarching initiative to deliver “unmetered intelligence,” where cutting-edge models tackle the most complex challenges while local models provide ongoing, cost-effective agent workflows. Ultimately, this advancement reflects a significant leap forward in how users can interact with their devices, enhancing productivity and streamlining tasks in everyday computing.
Description
Mercury represents an advanced family of diffusion large language models engineered to achieve top-tier LLM performance at remarkably fast speeds, processing over 1,000 tokens per second on commercial NVIDIA GPUs for immediate AI applications. These models are compatible with OpenAI and are designed to seamlessly replace traditional LLMs, facilitating easier integration into current AI frameworks. Among them, Mercury 2.5 stands out as the most sophisticated reasoning diffusion LLM, tailored for intricate applications where both performance and quality are priorities. It boasts a substantial 260K context window, enabling advanced reasoning, tool utilization, and structured output, with practical applications ranging from swift coding cycles to the development of agents, customer support solutions, and enterprise-level search functionalities. Additionally, Mercury Voice is specifically fine-tuned for voice agents, achieving a remarkable time-to-first-token of under 170 ms and supporting reasoning, tool use, structured output, and a 128K context window. This makes it highly suitable for various applications, including customer support, patient care, educational tools, and gaming experiences. Overall, the Mercury family is focused on pushing the boundaries of what AI can accomplish in real-time environments.
API Access
Has API
Yes
API Access
Has API
Yes
Integrations
Claude Haiku 4.5
No
GPT-5.6 Luna
No
Gemini 3.5 Flash-Lite
No
Git
Yes
GitHub
Yes
Microsoft Copilot
Yes
Model Context Protocol (MCP)
Yes
OpenAI
No
OpenClaw
Yes
PowerShell
Yes
Integrations
Claude Haiku 4.5
Yes
GPT-5.6 Luna
Yes
Gemini 3.5 Flash-Lite
Yes
Git
No
GitHub
No
Microsoft Copilot
No
Model Context Protocol (MCP)
No
OpenAI
Yes
OpenClaw
No
PowerShell
No
Pricing Details
No price information available.
Free Trial
No
Free Version
No
Pricing Details
$0.04 per 1M tokens
Free Trial
No
Free Version
Yes
Deployment
Web-Based
No
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
Yes
Mac
Yes
Linux
No
Chromebook
No
Deployment
Web-Based
Yes
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
Yes
In Person
No
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
Yes
In Person
No
Vendor Details
Company Name
Microsoft
Founded
1975
Country
United States
Website
blogs.windows.com/windowsdeveloper/2026/06/02/build-2026-furthering-windows-as-the-trusted-platform-for-development/
Vendor Details
Company Name
Inception
Country
United States
Website
www.inceptionlabs.ai/models