Fastest in Top Tier! Zhipu, Are You 'Spraying' Code?
量子位1919 字 (约 8 分钟)
82
Zhipu launched the GLM-5.1-highspeed API with a generation speed of 400 tokens/s, becoming the fastest flagship API among top-tier models, achieving high-speed inference through system engineering optimization and transforming AI programming and Agent interaction experiences.
入选理由：智谱GLM-5.1-highspeed API达到400 tokens/s生成速度，是顶流模型中最快的旗舰级API
FeaturedArticle#Zhipu#GLM-5.1#AI Inference#Code Generation#API中文