OpenAI's new Ultrafast API runs 14x faster on Cerebras, beating Claude
eyishazyer · x · 2026-08-15
Cerebras claims its chips make OpenAI 11x faster than Claude.
- New API Tier: OpenAI launched a limited preview called Ultrafast, running GPT-5.6 Sol on Cerebras hardware at 750 tokens/second, 14x faster than standard processing.
- Benchmarks: On the Humanity's Last Exam, GPT-5.6 Sol finished 2,500 questions in just over 11 hours, while Claude Fable 5 took more than three days.
- Use Cases: Ultra-fast speeds are critical for latency-sensitive products like voice, support, and coding agents.
Note: All figures are sourced from Cerebras, not independently verified.
Related event: OpenAI and Cerebras Preview Ultrafast Mode for GPT-5.6 Sol at 750 Tokens/s(20 posts)→
More from Companies & People
- MIT Biology and Schwarzman College hiring tenure-track professor in computational biology with generative AI focus — anshulkundaje · 2026-10-16
- DynaRobotics CEO Lindon Gao on running deployment and research feedback loops together — micoolcho · 2026-10-16
- Companies rushed in on AI. Now some are pulling back — return2ozma · 2026-10-16
- ai& × AMD Build Day hackathon in Tokyo: 8 teams, 4.5 hours, Chinese models allowed — DavidBennett__ · 2026-10-16
- Sakana AI opens first dedicated ISV, SI and CS roles in Japan GTM push — SakanaAILabs · 2026-10-16
- Kaggle teams with Google DeepMind and Zapier for inaugural Bench Summit — jocarrasqueira · 2026-10-16