Skip to content
latestai.eulatestai.eu
GU

GPT Ultrafast

by OpenAI

OpenAI API service tier running GPT-5.6 Sol up to 14x faster than Standard, at up to 750 tokens/sec on Cerebras hardware.

Limited in EULanguage ModelsPlatforms & InfraModel

Updated EU status checked Last shown

GPT Ultrafast at a glance

What is GPT Ultrafast?
GPT Ultrafast is a model from OpenAI. OpenAI API service tier running GPT-5.6 Sol up to 14x faster than Standard, at up to 750 tokens/sec on Cerebras hardware.
Who makes GPT Ultrafast?
GPT Ultrafast is made by OpenAI.
Does GPT Ultrafast work in the EU?
Limited in the EU. Ultrafast is only in a limited preview for select customers, with no region-specific availability stated. OpenAI's business products offer GDPR support, a DPA and data residency, but this is not confirmed for Ultrafast. Last verified 14 Nov 2026.
How much does GPT Ultrafast cost?
API pricing. No pricing published; limited preview for select API customers. Licence: Proprietary.
Where was GPT Ultrafast shown?
In 2 creator videos by AI Search, Matthew Berman. Most recently by AI Search on 16 Aug 2026, at 21:53 in “New Deepseek, GLM 5.3, Grok 4.6, LTX 2.5, Qwen 3.8, Gemini 3.7: AI NEWS”.

Sources: creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.

About

Ultrafast is a service tier in the OpenAI API that runs GPT-5.6 Sol, which OpenAI describes as its most intelligent model at the time of the announcement, at up to 14× the speed of Standard processing. It generates up to 750 output tokens per second and is powered by Cerebras, as part of OpenAI's partnership with the company on low-latency inference.

OpenAI positions it for time-sensitive workflows where speed has previously meant choosing a smaller model: incident response and log analysis, financial research and fraud detection, real-time customer support and voice, commerce assistance, and interactive research or experimentation loops. Named early testers include Jane Street, Podium, Basis and Rogo, and OpenAI says its own engineers use it for incident response and research.

Access is a limited preview, announced on August 13, 2026, for a select group of customers. OpenAI says it will expand access as capacity grows, and interested businesses can sign up for updates. No pricing, rate limits or general-availability date were given in the announcement.

Key features
  • Runs GPT-5.6 Sol up to 14× faster than Standard processing
  • Up to 750 output tokens per second
  • Powered by Cerebras inference hardware
  • Delivered as an OpenAI API service tier
  • Limited preview for select customers; sign-up for updates
2 moments

As seen on YouTube

Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.

Keep exploring

Similar AI tools

Closest neighbours by meaning, not just by category.

GS

GPT-5.6 Sol

Model · OpenAI

29

OpenAI's GPT-5.6 Sol frontier model, with an Ultrafast API tier on Cerebras reaching up to 750 output tokens per second.

Limited in EULanguage Models
Release date n/aAPI
UF

Ultra Fast mode

API · OpenAI

1

OpenAI high-speed inference tier that serves model output far faster than standard, reportedly around 14x.

UnverifiedPlatforms & Infra
Release date n/aAPI
GP

GPT-6.1

Model · OpenAI

1

OpenAI language model in the GPT-6.1 family; the Soul Max variant is noted by reviewers for low token use per task.

Available in EULanguage Models
Release date n/a
GS

GPT-6 Sol

Model · OpenAI

4

OpenAI's mid-tier GPT-6 model, positioned below GPT-6 Astra and above Luna, priced at $2/$10 per million tokens.

Available in EULanguage Models
Release date n/aPaid
GP

GPT-5.4

Model · OpenAI

2

OpenAI frontier language model used for coding, reasoning and agentic tasks, available via ChatGPT and the API.

Available in EULanguage Models
Release date n/aAPI
GP

GPT-5.5

Model · OpenAI

8

OpenAI language model available through ChatGPT, Codex and the API, used for coding, review and general tasks.

Available in EULanguage Models
Release date n/aFreemium