Mercury 2Inception
|
SubQSubquadratic
|
|||||
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
SubQ is a large language model developed by Subquadratic, designed specifically for long-context reasoning tasks. It can process up to 12 million tokens in a single prompt, allowing it to analyze entire codebases, long histories, and complex datasets at once. The model uses a sub-quadratic sparse-attention architecture that improves efficiency by focusing only on the most relevant relationships in the data. This approach reduces computational overhead while maintaining strong performance on large-scale tasks. SubQ is optimized for use cases such as software engineering, coding agents, and long-context retrieval. It delivers fast processing speeds and operates at a lower cost compared to many traditional models. Developers can access SubQ through APIs or integrate it into coding tools for enhanced workflows. Its architecture enables scalable AI reasoning without the limitations of standard transformer models.
|
|||||
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
Developers, AI engineers, and enterprises that need large-context language models for coding, data analysis, and advanced AI workflows
|
|||||
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
No information available.
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 InformationSubquadratic
Founded: 2026
United States
subq.ai/
|
|||||
Alternatives |
Alternatives |
|||||
|
|
|
|||||
|
|
|
|||||
|
|
|
|||||
|
|
|
|||||
Categories |
Categories |
|||||
Integrations
OpenAI
Cerebras
Claude Code
GPT-4.1
Groq
Inception Labs
LiveKit
OpenAI Codex
Pipecat
Retell AI
|
Integrations
OpenAI
Cerebras
Claude Code
GPT-4.1
Groq
Inception Labs
LiveKit
OpenAI Codex
Pipecat
Retell AI
|
|||||
|
|
|