Mercury 3 擴散式大語言模型標稱生成速度達每秒 1,068 個 token

Inception "Mercury 3", 1000 tok/s diffusion LLM (inceptionlabs.ai) 13 points by cmrdporcupine 12 minutes ago | hide | past | favorite | 2 comments help camdenclark 1 minute ago | next [–] Looks excellent, looking forward to trying this out. Feels like we're reaching a critical point where these become competitive. reply cmrdporcupine 11 minutes ago | prev [–] "Quality: On par or better than frontier speed-optimized models like GPT-6 Luna and Claude Haiku 5.5. Speed: 1,068 tokens per second on NVIDIA GPUs. Context: 1M tokens, up from 260K for Mercury 2.5 Price: $0.20 per million input and $0.70 per million output tokens. At launch, Mercury 3 is 50% off at $0.10 per 1M input and $0.35 per 1M output. Cached tokens are 90% off the input price." reply Consider applying for YC's Winter 2027 batch! Applications are open till November 2. Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact Search: