Back to all models
inception
inceptionInception: Mercury 2
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...
inception/mercury-2
Context Size
128K
Input Price
1,537.5 Ks/M
Output Price
4,612.5 Ks/M
Architecture
Text
Supported Parameters
include_reasoningmax_tokensreasoningresponse_formatstopstructured_outputstemperaturetool_choicetools
Details
TokenizerOther
Max Completion50,000 tokens
Provider Context128K tokens
ModeratedNo