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.
More from Infra
- Alibaba roadmap: Qwen explores RSI, new models up to 10T params, 20GW datacenters by 2032 — teortaxesTex · 2026-09-22
- Alibaba Plans AI Model With 5-10 Trillion Parameters, Unveils New Chip — tengo_harambe · 2026-09-22
- Meituan's unified recommendation foundation model MTFM lifts orders up to 6.68%, cut inference cost 24% — 美团技术团队 · 2026-09-22
- Is upgrading from 2x to 4x RTX 3090 worth it for local LLM work? — fgoricha · 2026-09-22
- Qwen-Image local on a 24GB MacBook Pro takes 5-6 minutes per image — vista8 · 2026-09-22
- Cerebras CEO on Jensen Huang: a decade trading as 'nobody' before Nvidia made it — rohanpaul_ai · 2026-09-22