Cerebras Powers OpenAI API Ultrafast Tier, Running GPT-5.6 at 750 Tokens/sec
Sethwinterroth · x · 2026-08-14
Cerebras announced that it now powers Ultrafast, a new service tier in OpenAI's API, running GPT-5.6 Sol at up to 750 output tokens per second.
This integration creates an entirely new point on the speed-intelligence frontier, enabling enterprises to build with frontier intelligence at real-time speeds. The service is designed to support faster coding agents, research systems that analyze information in seconds, and enterprise agents that reason and act without latency. GPT-5.6 Sol Ultrafast is currently beginning with a limited API preview, with capacity expected to grow over time.
Related event: OpenAI and Cerebras Preview Ultrafast Mode for GPT-5.6 Sol at 750 Tokens/s(20 posts)→
More from Infra
- TokenSpeed MLA 2 hits Vera Rubin: up to 3.44× faster MLA decode for Kimi K3 — zhyncs42 · 2026-10-16
- US vs Chinese hyperscalers: Americans fund and schmooze, Chinese demand your BoM and cap you at 7% margin — jwt0625 · 2026-10-16
- How LiteLLM routes one OpenAI-shaped API across every model provider — Mahmoud_Zalt · 2026-10-16
- OpenAI-Broadcom custom AI chip Jalapeño named a TIME Best Invention of 2026 — itsclivetime · 2026-10-16
- Developer live-runs continual pretraining of a Luganda LLM on Colab, 41% done with loss dropping fast — weskambale · 2026-10-16
- Jensen Huang: Nvidia charges ~$thousands per GPU yearly for software, a major revenue line — rohanpaul_ai · 2026-10-16