OpenAI removes Ultrafast tier from GPT-5.6 Sol in Codex, fueling GPT-6 Sol rumors

imjustnewatai · x · 2026-09-22

A user spotted that OpenAI quietly removed the Ultrafast service tier from gpt-5.6-sol's Codex entry, even though Ultrafast still exists in OpenAI's API, where it's described as "the fastest available responses for latency-sensitive work." Ultrafast can currently push GPT-5.6 Sol to 750 output tokens/sec — about 14x standard speed — via Cerebras. The removal could be routine cleanup, but the timing right before DevDay suggests GPT-6 Sol may soon replace 5.6 Sol. Unconfirmed rumor.

Original post →

More from Infra

Infra channel →