---
title: "OpenAI's Ultrafast mode runs GPT-5.6 Sol 14x faster"
url: https://www.parallelquant.com/posts/openai-s-ultrafast-mode-runs-gpt-5-6-sol-14x-faster-7bd0be
source_name: "OpenAI"
source_url: https://openai.com/index/previewing-ultrafast
published: 2026-08-13T10:00:00.000Z
topics: ["llms", "products", "chips"]
publisher: "Parallel Quant"
---

# OpenAI's Ultrafast mode runs GPT-5.6 Sol 14x faster

*2026-08-13 · Source: [OpenAI](https://openai.com/index/previewing-ultrafast)*

OpenAI is previewing "Ultrafast," a new API service tier that runs GPT-5.6 Sol up to 14 times faster than standard, powered by Cerebras hardware. It delivers up to 750 output tokens per second.

**Why it matters:** Cerebras powering this speedup gives it a marquee customer at a time when its hardware sales have reportedly struggled elsewhere, despite cloud growth. Faster inference also directly targets enterprise use cases like agents and real-time applications, where latency has been a practical bottleneck for GPT-class models.

**Topics:** llms, products, chips

---
Read the original: https://openai.com/index/previewing-ultrafast
Canonical: https://www.parallelquant.com/posts/openai-s-ultrafast-mode-runs-gpt-5-6-sol-14x-faster-7bd0be
Published by Parallel Quant — https://www.parallelquant.com