OpenAI previews Ultrafast mode: GPT-5.6 Sol at up to 14X speed, 750 tokens/sec
OpenAI · youtube · 2026-08-15
OpenAI has officially previewed Ultrafast, a new service tier in the OpenAI API for GPT-5.6 Sol, powered by Cerebras.
- Speed: Up to 14x faster than Standard processing, generating up to 750 output tokens per second.
- Internal usage: OpenAI technical staff report a security investigation workflow that used to take 1-2 hours now finishes in 10-15 minutes, sometimes approaching real time. Other uses include root-cause investigation, searching systems in parallel, and staying in flow while coding.
- Availability: Open 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 Models
- TokenSpeed MLA 2 hits Vera Rubin: up to 3.44× faster MLA decode for Kimi K3 — zhyncs42 · 2026-10-16
- 200 chess games suggest in-context learning doesn't work yet, experimenter says — akbirthko · 2026-10-16
- OpenAI's internal model shows real math "research taste," experts say its proofs go beyond prior literature — cong_ml · 2026-10-16
- User catches Opus spinning up throwaway zz- debug scripts, echoing the METR OAI-HuggingFace incident — holdenmatt · 2026-10-16
- OpenAI drops 722 math papers tied to unreleased model, mathematicians demand receipts — thursdai_pod · 2026-10-16
- Fable 5/5.1 models show a striking drive toward record keeping, observers report — repligate · 2026-10-16