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 >1,000 tokens/sec on standard GPUs. Mercury 2 is 5x+ faster than leading speed-optimized LLMs like Claude 4.5 Haiku and GPT 5 Mini, at a fraction of the cost. Mercury 2 supports tunable reasoning levels, 128K context, native tool use, and schema-aligned JSON output. Built for coding workflows where latency compounds, real-time voice/search, and agent loops. OpenAI API compatible. Read more in the [blog post](https://www.inceptionlabs.ai/blog/introducing-mercury-2).
Quality Index
32.8
84th of 442
Top 19%
Coding Index
30.6
74th of 352
Top 21%
Price/1M
$0.38
357th cheapest
21% above median
Top 53%
Speed
771 tok/s
Top 0%
TTFT
3.95s
Context Window
128K
225th largest
Top 75%
Input
$0.25
per 1M tokens
Output
$0.75
per 1M tokens
Blended
$0.38
per 1M tokens
Cheaper than 47% of models. Median price is $0.31/1M tokens.
Daily
$0.38
Monthly
$11.25
771
tokens/sec
Faster than 100% of models
3.95
seconds
Faster than 10% of models
3.95
seconds
Faster than 26% of models
Market Median
46 tok/s
1591% faster
Median TTFT
0.42s
845% slower
Throughput/Dollar
2056
tok/s per $/1M
Speed Comparison
Context Window
128K
tokens
Larger than 25% of models
Max Output
50K
tokens
39% of context