Loading...
Loading...
Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...
Input
$0.25
per 1M tokens
Output
$0.75
per 1M tokens
Blended
$0.38
per 1M tokens
Cheaper than 57% of models. Median price is $0.56/1M tokens.
Daily
$0.38
Monthly
$11.25
777
tokens/sec
Faster than 100% of models
3.58
seconds
Faster than 19% of models
3.58
seconds
Faster than 48% of models
Market Median
86 tok/s
805% faster
Median TTFT
1.07s
234% slower
Throughput/Dollar
2072
tok/s per $/1M
Speed Comparison
Context Window
128K
tokens
Larger than 22% of models
Max Output
50K
tokens
39% of context
Quality Index
32.8
125th of 507
Top 25%
Coding Index
30.6
113th of 417
Top 27%
Price/1M
$0.38
269th cheapest
33% below median
Top 43%
Speed
777 tok/s
Top 0%
TTFT
3.58s
Context Window
128K
284th largest
Top 78%