# OpenAI Previews an Ultrafast Tier Running GPT-5.6 Sol on Cerebras Wafer-Scale Chips at Up to 750 Tokens per Second

OpenAI says the tier runs up to 14 times faster than standard serving, but the company has not published a price, a general availability date, or any independent latency measurements.

- Published: 2026-08-16T06:12:17.236Z
- Canonical: https://polylog.news/ai/2026-08-16/openai-previews-an-ultrafast-tier-running-gpt-5-6-sol-on-cer
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [OpenAI](https://openai.com/index/previewing-ultrafast/), [Cerebras](https://www.cerebras.ai/blog/accelerating-gpt-5-6-sol-ultrafast-with-openai), [The Decoder](https://the-decoder.com/gpt-5-6-sol-goes-14x-faster-as-openai-launches-ultrafast-mode-powered-by-cerebras/), [Help Net Security](https://www.helpnetsecurity.com/2026/08/14/openais-gpt-5-6-sol-runs-up-to-14x-faster-with-ultrafast-mode/)

OpenAI on August 14 [previewed Ultrafast](https://openai.com/index/previewing-ultrafast/), an application programming interface (API) service tier that serves the same GPT-5.6 Sol weights at up to 14 times the speed of standard processing, reaching roughly 750 output tokens per second. Access is by invitation during the preview.

The hardware explains the speed gain. [Cerebras confirmed its wafer-scale engines run the tier](https://www.cerebras.ai/blog/accelerating-gpt-5-6-sol-ultrafast-with-openai), keeping 44 gigabytes of on-chip static random-access memory (SRAM) so that decoding is not limited by off-chip memory bandwidth in the way a conventional graphics processing unit deployment is. That is the mechanism behind the faster token rate, and it is why the speedup does not require a smaller or distilled model.

Two things are missing, and they determine whether the announcement changes anything in practice. OpenAI has not disclosed Ultrafast pricing, and [the published GPT-5.6 Sol rate of $5 per million input tokens and $30 per million output tokens applies only to the Standard and Fast tiers](https://the-decoder.com/gpt-5-6-sol-goes-14x-faster-as-openai-launches-ultrafast-mode-powered-by-cerebras/). There is also no general availability date and no independent reproduction of the latency figures, which so far come only from the two vendors involved. [Reported target workloads](https://www.helpnetsecurity.com/2026/08/14/openais-gpt-5-6-sol-runs-up-to-14x-faster-with-ultrafast-mode/) are coding, finance, support, commerce, research and incident response, all cases where an agent loop makes many sequential model calls and latency adds up across each one.

## What this means

Serving speed is becoming a product tier rather than a fixed property of a model, and that changes which agent architectures are affordable to run. Multi-step agents accumulate latency with every additional step, so a 14-times decode speedup makes deep tool-use chains viable that were previously too slow for interactive use. That favors OpenAI's Codex and ChatGPT Work products over rivals serving comparable models on standard graphics processing unit fleets. Cerebras gains a marquee customer in the high-end inference market, and Nvidia faces a challenge not in training but in the specific economics of low-latency decoding. The unresolved question is price. If Ultrafast carries a large premium, it stays a niche tier for latency-critical work. If it prices near standard rates, it resets the default for how agents are served.

## What to watch

- The published Ultrafast price relative to the standard GPT-5.6 Sol rate, which decides whether this is a niche option or the new default for agents.
- Independent latency and throughput measurements from customers rather than from OpenAI or Cerebras.
- Whether Anthropic or Google introduce their own dedicated fast-decode tiers, which would confirm serving speed as a competitive factor separate from model quality.