Mercury 2.5
Inception · text → text
Mercury 2.5 is Inception's diffusion language model (dLLM), designed for text generation and reasoning tasks. Instead of sequential generation, it produces and refines multiple tokens in parallel to achieve rapid reasoning, supported by an expansive 260,000-token context window.
Input$0.2 /M
Output$0.75 /M
Cache read$0.02 /M