OpenAI previews GPT-5.6 Sol at up to 14x standard speed
Cerebras hardware drives the API tier to 750 output tokens per second, with access restricted to selected customers while capacity grows.
By RuntimeWire Staff · Published · Updated
Primary source: OpenAI on X
Why it matters
OpenAI is making inference speed a distinct API product for voice, coding and operational systems where latency limits usage. Its reach now depends on how quickly Cerebras capacity enters production.
Cerebras hardware drives the API tier to 750 output tokens per second, with access restricted to selected customers while capacity grows.
When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.