Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
Mercury 2.5 represents the pinnacle of production models from Inception, demonstrating a remarkable enhancement in quality compared to its predecessor, Mercury 2, all while upholding an impressive low-latency serving profile. It stands out as the most advanced diffusion language model currently available and is touted by Inception as the largest diffusion LLM ever developed. With a 40% boost in intelligence over Mercury 2, its performance aligns closely with that of cost-efficient frontier models like GPT-5.6 Luna (Low), Gemini 3.5 Flash-Lite, and Claude Haiku 4.5. The model boasts a generation speed of 1,107 tokens per second on commonly accessible NVIDIA GPUs and accommodates a generous 260K-token context window. Among its features are adjustable reasoning capabilities, simultaneous tool calls, and JSON that aligns with schemas. Specifically engineered for latency-sensitive tasks, it is well-suited for scenarios involving numerous model calls during a single interaction. In applications such as search agents and RAG pipelines, Mercury 2.5 excels in functions like planning, query rewriting, re-ranking, fact structuring, source summarization, and answer verification, all while ensuring rapid response times, making it an essential tool for developers seeking efficiency in their workflows.
Description
NVIDIA's Nemotron 3.5 Lightning is a state-of-the-art mixture-of-experts model boasting 30 billion parameters, of which 3 billion are actively utilized, specifically engineered for efficient, high-throughput performance in long-duration and continuously operating AI agents. This model is tailored for the execution components of agentic systems, adeptly managing frequent operations like tool invocations, output verification, routine commands, and delegating tasks to subagents, while larger reasoning models concentrate on strategic planning and orchestration. By employing a mixture-of-experts architecture, it activates only a select subset of parameters for each input token, marrying the expansive capacity of a larger model with significantly reduced computational demands. The training of this model is optimized for widely used agent harnesses and enhances inference speed through techniques such as speculative decoding, multi-token prediction, DFlash, and DSpark, making it versatile across various operational scenarios. Additionally, it is compatible with BF16 and NVFP4 checkpoints, providing flexibility in deployment from local systems like DGX Spark and GeForce RTX hardware to extensive data center infrastructures. In summary, its innovative design and scalability make it a powerful tool for advancing AI capabilities.
API Access
Has API
API Access
Has API
Integrations
Hermes Agent
JSON
NVIDIA NemoClaw
OpenClaw
Portable Computer by Perplexity
Integrations
Hermes Agent
JSON
NVIDIA NemoClaw
OpenClaw
Portable Computer by Perplexity
Pricing Details
No price information available.
Free Trial
Free Version
Pricing Details
No price information available.
Free Trial
Free Version
Deployment
Web-Based
On-Premises
iPhone App
iPad App
Android App
Windows
Mac
Linux
Chromebook
Deployment
Web-Based
On-Premises
iPhone App
iPad App
Android App
Windows
Mac
Linux
Chromebook
Customer Support
Business Hours
Live Rep (24/7)
Online Support
Customer Support
Business Hours
Live Rep (24/7)
Online Support
Types of Training
Training Docs
Webinars
Live Training (Online)
In Person
Types of Training
Training Docs
Webinars
Live Training (Online)
In Person
Vendor Details
Company Name
Inception
Country
United States
Website
www.inceptionlabs.ai/blog/introducing-mercury-2-5
Vendor Details
Company Name
NVIDIA
Founded
1993
Country
United States
Website
nvidia.com