OpenAI previews Ultrafast: a GPT-5.6 Sol API tier on Cerebras hitting 750 tokens/sec
thione · x · 2026-08-18
OpenAI previewed Ultrafast, a new GPT-5.6 Sol API tier powered by Cerebras inference, delivering up to 750 output tokens per second — a major speed play targeting latency-sensitive workloads.
Related event: OpenAI Previews Cerebras-Powered Ultrafast at 750 Tokens/sec(3 posts)→
More from Infra
- New hardware day: local LLM deployment the moment it arrives — lxfater · 2026-10-16
- Together AI's score centering fixes RL training collapse under quantized inference — nrehiew_ · 2026-10-16
- Inference is splitting prefill and decode across specialized chips, not just H100s — AccBalanced · 2026-10-16
- Rebasely launches in beta: Git hosting built for humans and coding agents — handotdev · 2026-10-16
- Drama3 TTS lands in audio.cpp: up to 5x real-time on RTX 5090, <8GB VRAM mode too — Acceptable-Cycle4645 · 2026-10-16
- Three CoreWeave co-founders have sold $3.3B in shares since IPO amid credit worries — SumitGup · 2026-10-16