Inception: Mercury 2 Inception

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...

Architecture

  • Modality: text->text
  • InputModalities: text
  • OutputModalities: text
  • Tokenizer: Other

ContextAndLimits

  • ContextLength: 128000 Tokens
  • MaxResponseTokens: 50000 Tokens
  • Moderation: Disabled

Pricing

  • Prompt1KTokens: 2.5e-07 ₽
  • Completion1KTokens: 7.5e-07 ₽
  • InternalReasoning: ₽
  • Request: ₽
  • Image: ₽
  • WebSearch: ₽