Mercury 2
inception/mercury-2Mercury 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...
$0.25Input, per million tokens
$0.75Output, per million tokens
128KContext window
50KLongest answer
128K tokens of context — about 96,000 words, on a scale that ends at 2M.
What it can do
- Reasoning
- Tool use
- Takes text
- Gives text
Released 4 Mar 2026 · checked 3 Oct 2026.