About
Mercury is the first diffusion large language model (dLLM). Applying a breakthrough discrete diffusion approach, the model runs 5-10x faster than even speed optimized models like GPT-4.1 Nano and Claude...
Pricing
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 $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.38
Monthly
$11.25
vs. Similar Models
Inception: Mercury 2
$0.380%
Inception: Mercury Coder
$0.380%
Llama Guard 3 8B
$0.37-1%
Qwen: Qwen3 VL 235B A22B Instruct
$0.37-1%
Performance
Context Window
128K
tokens
Larger than 16% of models
Max Output
32K
tokens
25% of context
Context Window Comparison
Inception: Mercury 2
128KSame
Perplexity: Sonar Reasoning Pro
128KSame
Upstage: Solar Pro 3
128KSame