SYLIN

Mercury

by Inception · Model · Language & code models

Mercury 2.5 diffusion LLM runs at 1,107 tokens/s on widely available NVIDIA GPUs, with 260K context

Evidence

  1. Nov 13
    Inception Labs is reportedly discontinuing the Mercury models API
  2. Sep 8
    Priced $0.20/M input and $0.75/M output tokens; launch promotion 80% off; 100M free API tokens
  3. Sep 8
    Claims 40% intelligence gain over Mercury 2, comparable to GPT-5.6 Luna (Low), Gemini 3.5 Flash-Lite, Claude Haiku 4.5
  4. Sep 8
    Output reported good and very fast; a refusal classifier blocked questions about its architecture, three errors in one agent turn
  5. Sep 8
    Preview tested as usable general chatbot, comparable to some last-gen open-weights models, but worse at agentic coding with custom harness