OpenAI 推出 Ultrafast 模式，GPT-5.6 Sol 速度提升 14 倍
原标题：GPT-5.6 Sol goes 14x faster as OpenAI launches Ultrafast mode powered by Cerebras
AI 摘要
OpenAI 推出 GPT-5.6 Sol 的“Ultrafast”模式预览，通过 Cerebras 硬件实现每秒 750 个输出 token，速度提升 14 倍。该服务初期仅通过 API 向特定客户提供，并计划逐步扩大。OpenAI 旨在将小模型的速度与大模型的推理能力结合，应用于事件响应、金融、客服、电商和研究等场景，同时通过分层定价将速度作为盈利杠杆。
正文节选
GPT-5.6 Sol goes 14x faster as OpenAI launches Ultrafast mode powered by Cerebras OpenAI is launching a preview of its new "Ultrafast" mode, which delivers up to 750 output tokens per second from its flagship model, GPT-5.6 Sol. The inference acceleration comes from Cerebras, which signed a ten-billion-dollar partnership with OpenAI earlier this year. The service will initially be available only through the OpenAI API for GPT-5.6 Sol and limited to select customers. OpenAI plans to expand access