Mercury 2Inception
|
||||||
Related Products
|
||||||
About
Mercury 2 is the first reasoning model fast enough to pick up the phone, a reasoning diffusion language model built for real-time voice agents. Instead of making callers wait through seconds of dead air while an autoregressive model generates thinking tokens one by one, Mercury 2 uses a diffusion large language model architecture to generate tokens in parallel, decoding 1000+ tokens per second on standard NVIDIA GPUs. That speed is fast enough to run a full reasoning pass and start speaking within the latency budget of a natural conversation, reducing the cost of reasoning from seconds of silence to roughly 300 milliseconds. Mercury models work by corrupting clean text into noise, then training a standard Transformer to reverse the process and predict clean text across all positions simultaneously. Because each denoising pass touches many tokens, generation uses the GPU more efficiently than one-token-at-a-time decoding, making custom-silicon-like speed possible on NVIDIA H100s.
|
About
MercuryDPM is an open source code for discrete particle simulations, designed to simulate the motion of particles or atoms by applying forces and torques from external body forces, such as gravity or magnetic fields, and from particle interaction laws. For granular particles, these forces are typically contact forces, including elastic, plastic, viscous, and frictional interactions, while molecular simulations can use interaction potentials such as Lennard-Jones. MercuryDPM is written as a versatile, object-oriented C++ code and is built to be understandable, flexible, and extensible for researchers and engineers who need to create new simulation models. It is developed extensively for granular applications, while remaining adaptable to other particle-based systems and long-range interactions. Its documentation guides users through installation, running simulations, visualization, analysis, and creating new MercuryDPM codes to model systems of their choice.
|
|||||
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
|||||
Audience
Voice AI infrastructure teams that need low-latency reasoning models for phone agents, tool-calling workflows, and natural customer conversations
|
Audience
Researchers, DEM developers, and process engineers who need a particle simulation code for modeling contact forces
|
|||||
Support
Phone Support
24/7 Live Support
Online
|
Support
Phone Support
24/7 Live Support
Online
|
|||||
API
Offers API
|
API
Offers API
|
|||||
Screenshots and Videos |
Screenshots and Videos |
|||||
Pricing
No information available.
Free Version
Free Trial
|
Pricing
Free
Free Version
Free Trial
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Webinars
Live Online
In Person
|
Training
Documentation
Webinars
Live Online
In Person
|
|||||
Company InformationInception
United States
www.inceptionlabs.ai/blog/mercury-2-the-first-reasoning-model-fast-enough-to-pick-up-the-phone
|
Company InformationMercuryDPM
Founded: 2009
United States
www.mercurydpm.org
|
|||||
Alternatives |
Alternatives |
|||||
|
|
|
|||||
|
|
||||||
|
|
|
|||||
|
|
|
|||||
Categories |
Categories |
|||||
Integrations
C++
Cerebras
GPT-4.1
Groq
Inception Labs
LiveKit
OpenAI
Pipecat
Retell AI
Vapi AI
|
Integrations
C++
Cerebras
GPT-4.1
Groq
Inception Labs
LiveKit
OpenAI
Pipecat
Retell AI
Vapi AI
|
|||||
|
|
|