OpenAI Previews Ultrafast Mode for GPT-5.6 Sol at 14X Speed
OpenAI · youtube · 2026-08-14
OpenAI has officially previewed Ultrafast mode, a new service tier designed for the GPT-5.6 Sol model, powered by Cerebras hardware.
- Extreme Speed: The new tier runs up to 14x faster than standard processing, generating up to 750 output tokens per second.
- Workflow Transformation: The massive speed is changing behaviors. A security investigation workflow that previously took 1–2 hours now completes in 10–15 minutes, approaching real-time. Staff also use it to investigate root causes, search systems in parallel, and maintain flow while coding.
- Availability: Ultrafast mode is currently available to a select group of API customers, with access expanding as capacity grows.
Related event: OpenAI and Cerebras Preview Ultrafast Mode for GPT-5.6 Sol at 750 Tokens/s(20 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