OpenAI announced a preview of Ultrafast mode, serving GPT-5.6 Sol at up to 750 output tokens per second, about 14x the standard mode. Inference runs on Cerebras wafer-scale hardware instead of GPUs. Access is limited to a small preview group, and pricing is undisclosed.
OpenAI previews Ultrafast mode: GPT-5.6 Sol on Cerebras at up to 750 tok/s
2026-08-13Verified announcementWATCH
OpenAI announced a preview of Ultrafast mode, serving GPT-5.6 Sol at up to 750 output tokens per second, about 14x the standard mode. Inference runs on Cerebras wafer-scale hardware instead of GPUs. Access is limited to a small preview group, and pricing is undisclosed.
Referenceopenai.com · previewing ultrafastReferencetechcrunch.com · openai introduces ultrafast a new mode that makes gpt 5 6 sol work at 14x the speed
Imported from the existing research archive. Migration preserves the recorded judgment and is not a fresh verification.
What this means for you
This is the first time OpenAI serves a frontier model on third-party, non-GPU inference silicon. It validates alternative inference hardware at frontier quality, and it signals that speed-tiered API products are becoming the next competitive axis.
Evidence & related material
Technical details & scores
| Speed Output Toks | 750 |
|---|---|
| Speedup | 14x |
| Hardware | Cerebras wafer-scale |
| Access | limited preview |
| Pricing | undisclosed |
Technical impact 4
Engineering value 3
Adoption signal 2
Maturity 2
Verification cost 4
Risk 3