AIHacker Newsabout 2 hours ago
Mercury 2.5 LLM Released at 770 Tokens/sec
7 min read
Mercury 2.5, a reasoning-focused large language model, launched on September 8, 2026, delivering 770.4 tokens per second output speed via Inception's API. It scores 12 on the Artificial Analysis Intelligence Index, below the median of 13 for comparable models, while offering competitive pricing at $0.25 per million input and $0.75 per million output tokens. The model features a 260k-token context window and supports text input and output.
Level
Hype check
Tap to vote and see what everyone thinks.