Mercury 2on Krater.ai
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
Released March 4, 2026
Specifications
Mercury 2 at a glance
Context
128K tokens
Max output
50K tokens
Input
Text
Output
Text
Input price
$0.25 / 1M
Output price
$0.75 / 1M
Capabilities
What it is good at
Catalog capabilities
- Generates text responses
- Supports tool calling
- Supports structured outputs
Good for
Benchmarks
Catalog data, not Krater benchmarks.
Coding index score
31.1
Agentic index score
1.6
Intelligence index score
13.8
Design Arena asciiart rank
#69
Design Arena svg rank
#83
Compare
Compare Mercury 2
Mercury 2 vs Mercury 2.5
Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception.
Open comparisonMercury 2 vs Mercury 2.5 Preview
Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception.
Open comparisonMercury 2 vs Mercury Coder
Mercury Coder is the first diffusion large language model (dLLM).
Open comparisonFAQ
Questions about Mercury 2
Clear answers based on the model catalog and Krater access.