Cerebras

GPT-6.1 Sol Ultrafast - gpt 6 1 sol ultrafast chatgpt work codex api a supersonic passenger jet with a drooped nose

OpenAI Rolls Out GPT-6.1 Sol Ultrafast on ChatGPT Work, Codex, and API

OpenAI has rolled out Ultrafast mode for GPT-6.1 Sol in the API, Codex and ChatGPT Work, promising up to 8x faster generation than Sol Standard. It costs $12 per million input tokens and $60 per million output, six times Standard, and in ChatGPT it is limited to Pro $500 and eligible Enterprise and Edu plans. We cover the measured speed, every price tier, the 8x allowance burn, EU residency, the Cerebras question and when the premium pays.

Read more
openai ultrafast api playground speed selector a speedometer gauge with needle at maximum

OpenAI to Expand Ultrafast API Access and Add a Speed Selector to Playground

OpenAI is preparing to widen access to Ultrafast, its Cerebras-powered API tier that runs GPT-5.6 Sol up to 14 times faster than Standard, and its Playground code now holds a hidden Standard, Fast and Ultrafast speed selector. We checked the code and the API specification ourselves. This article explains how the tiers fit together, what 750 tokens per second means, what is known about price and model support, where the speed pays off and how to prepare before DevDay.

Read more
CHAT