Which models and services support Ultrafast?

Ultrafast is available for GPT-6 Astra in Codex, ChatGPT Work, and the API, with GPT-6.1 Sol coming soon. It was previously previewed on GPT-5.6 Sol.

How much faster is Ultrafast than standard mode?

OpenAI says Ultrafast runs up to 8x faster than Astra Standard and 4x faster than Astra Fast in Codex, and up to 6x faster in the API. It delivers 300 tokens per second in Codex.

Large Language ModelsAI Coding AssistantsAI Business & IndustryGIGAZINE AISep 30, 2026Sep 30, 2026, 13:00 JST

OpenAI brings Ultrafast to GPT-6 Astra, 8x faster in Codex

Send on LINE

3 Key Points

What happened
OpenAI said Ultrafast is available today for GPT-6 Astra in Codex, ChatGPT Work, and the API, running up to 8x faster than Astra Standard and 4x faster than Astra Fast, with 300 tokens per second in Codex.
Why it matters
Developers and teams using GPT-6 Astra can now generate output up to 8x faster than the standard mode and 4x faster than the Fast mode when building in Codex, according to OpenAI.
What to watch
Access in Codex and ChatGPT Work hinges on subscribing to the new Pro 500 plan, and the body does not say whether existing Plus or Team subscribers can use Ultrafast without upgrading.

WHO IT HITSEnterprise developers and product teams who build on OpenAI's API or use Codex and ChatGPT Work and need higher throughput will have to weigh the new Pro 500 plan against their current usage limits. The speed gain matters most for workloads where token generation speed is the bottleneck, though the body does not name specific customer segments.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, every morning.

Get these free every morning

FAQ

Which models and services support Ultrafast?: Ultrafast is available for GPT-6 Astra in Codex, ChatGPT Work, and the API, with GPT-6.1 Sol coming soon. It was previously previewed on GPT-5.6 Sol.
How much faster is Ultrafast than standard mode?: OpenAI says Ultrafast runs up to 8x faster than Astra Standard and 4x faster than Astra Fast in Codex, and up to 6x faster in the API. It delivers 300 tokens per second in Codex.

GIGAZINE AIRead Original Article

Send on LINE

Also reported by ITmedia AI＋

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Get it free

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.