Megadose AI progress, ranked and analyzed.

Mercury 2.5 LLM hits 770 tokens per second

· HN · LLMs ·
Artificial Analysis clocks Mercury 2.5 at 780.8 output tokens per second, second-fastest in its comparison set.

The Inception proprietary reasoning model scores 12 on the Artificial Analysis Intelligence Index, described as below average for comparable models. It is priced at $0.25 per 1M input tokens and $0.75 per 1M output tokens, with a 260k-token context window. The page says it is text-only, API-available through one provider, and relatively concise in benchmark token use. HN · LLMs' note

score 5

Categories: Model Releases

Discussions

  • hn · 100 points · 61 comments
  • hn · 102 points · 62 comments
  • hn · 104 points · 63 comments
  • hn · 107 points · 64 comments