详细内容
Announcing our $50M Seed Round, led by Menlo Ventures
The Fastest LLMs
Ever Built
Diffusion LLMs: A Breakthrough for Speed and Quality
Need suggestions?
By using Mercury, you agree to our Terms of Use and have read our Privacy Policy
Powering Cutting-Edge AI Applications
The Mercury Diffusion Models
Blazing fast inference with frontier quality at a fraction of the cost.
The Diffusion Difference From Sequential to Parallel Text Generation
All other LLMs generate text one token at a time. Mercury diffusion LLMs (dLLMs) generate tokens in parallel, increasing speed and maximizing GPU efficiency.
See the difference
How it works
AI Applications Made Possible with Mercury
Lightning-fast code editing
Stay in flow with responsive autocomplete, intelligent tab suggestions, fast chat responses, and more.
Real-time voice agents
Engage naturally with AI for customer support, translation, and beyond.
Fast, creative co-pilots
Supercharge editorial and creative work—less waiting, more creating.
Rapid enterprise search
Instantly surface the right data from across your organization’s knowledge base.
Seamless enterprise workflows
Automate complex routing, analytics, and decision processes with ultra-responsive AI.
Our Models
Mercury Coder
dLLM optimized to accelerate coding workflows
Streaming, tool use, and structured output
128K context window
Input $0.25 | Output $1 per 1M tokens
Mercury
General-purpose dLLM that provides ultra-low latency
Streaming, tool use, and structured output
128K context window
Input $0.25 | Output $1 per 1M tokens
An Enterprise AI Partner
We’re available through major cloud providers like AWS Bedrock. Talk with us about fine-tuning, private deployments, and forward-deployed engineering support.
Integrate in Seconds
Our models are OpenAI API compatible and a drop-in replacement for traditional LLMs.
Providers
Inception 
\
\
OpenRouter Quora 
\
\
AWS Bedrock
Azure Foundry
What Customers are Saying
"I was amazed by how fast it was. The multi-thousand tokens per second was absolutely wild, nothing like I've ever seen."
Jacob Kim
Software Engineer
"After trying Mercury, it's hard to go back. We are excited to roll out Mercury to support all of our voice agents."
Oliver Silverstein
CEO
"We cut routing and classification overheads to sub-second latencies even on complex agent traces."
Damian Tran
CEO
NextGenAIisHere