OpenAI prepares broader rollout of Ultrafast API offering up to 750 tokens/sec
testingcatalog · x · 2026-09-26
TestingCatalog spotted multiple new references across OpenAI Platform and API docs suggesting a wider rollout of the Ultrafast API mode around DevDay on September 29.
- A hidden speed selector for the Responses API Playground would let developers pick Standard, Fast, or Ultrafast processing.
- OpenAI previously previewed Ultrafast with GPT-5.6 Sol: up to 750 output tokens per second and up to 14× faster inference than Standard.
- Access is currently limited to select customers, and OpenAI confirmed the mode is powered by Cerebras, tied to a 750 MW partnership with staged capacity through 2028.
- For developers the key trade-off is economics: reserving higher-cost, low-latency inference for latency-sensitive workloads.
- It remains unconfirmed whether all GPT-6 family models will support Ultrafast at launch.
Related event: OpenAI to Expand Ultrafast API Tier With Speeds Up to 750 Tokens Per Second(4 posts)→
More from Infra
- Nan Ya Plastics to spend NT$11.53B on fifth glass fabric plant on AI server demand — zephyr_z9 · 2026-11-11
- Three years building CPUs and spiking nets: one engineer's path to AI accelerators — k7agar · 2026-11-11
- CoreWeave: 2027 GPU renewals could add ~$4B annualized revenue, analyst skeptical — zephyr_z9 · 2026-11-11
- Running DeepSeek 4.1 locally on an $800 rig with a used RTX 3090 at 2-3 tok/s — LankyGuitar6528 · 2026-11-11
- Mark Says George Hotz Was Prescient About Nvidia's Situation — mark_k · 2026-11-11
- Amazon Prime 360 uses AI to rebuild NBA plays in 3D for live, any-angle replays — import_jmr · 2026-11-11