AI 资讯

Previewing Ultrafast mode: GPT-5.6 Sol at up to 14X the speed

2026年08月13日 18:00 3 次阅读来源：OpenAI Blog

Preview Ultrafast, a new OpenAI API service tier that runs GPT-5.6 Sol up to 14× faster. Powered by Cerebras, it delivers up to 750 output tokens per second.

本文内容来源于互联网，版权归原作者所有

查看原文

# Product

Previewing Ultrafast mode: GPT-5.6 Sol at up to 14X the speed

相关文章

Designing Spoiler Controls and Evidence Labels for a Horror Game Wiki

From OpenSpec to AIDLC: How I Improved My Team's AI Code Quality

Designing Game Wiki Guides Around Dependencies: A Big Ambitions Example

Fail-open is the default failure mode of agent hooks

The Lead Doesn't Write Code

Password-Reset 2FA Evidence: SMS OTP, TOTP Apps, and Email Fallbacks