Az Inception Labs kiadta a nagy sebességű Mercury modellt valós idejű kódoló asszisztensekhez
Inception Labs released an upgraded version of Mercury, its flagship model that delivers higher quality than Claude 4.5 Haiku at one-fifth the latency and less than one-quarter the price. The model is designed to be fast enough for real-time autocomplete, voice agents, and in-the-flow coding assistants.
- Priced at $0.25 per 1M input tokens and $1.00 per 1M output tokens
- Diffusion-based model that generates text similarly to image models
- Demonstrated extreme speed in generating working code
- Optimized for real-time applications including voice and autocomplete
Kapcsolódó hírek