seventy
AnnouncementOpenAI News22 September 2026

OpenAI improves GPT-6 caching of repeated prompts to speed responses and cut bills

What happened

OpenAI has changed how GPT-6 reuses repeated prompt content, so more requests are served from stored results. It also added tools to see why a reuse failed, markers you can place yourself, and settings to tune the behaviour, aimed at lower delay and spend.

Why it matters

If your GPT-6 prompts repeat large shared prefixes, OpenAI's new caching controls let you cut both latency and spend.

Impact

AI & developer tools · Software & SaaS

Higher cache hit rates and new controls cut latency and costs.

Ask your team

Which of our GPT-6 prompts share long repeated prefixes, and are we using the new caching controls?

Connecting the dots

Before
Last OpenAI story: V7 builds agents on GPT-5.6 that use company files and cite sources (22 Sep) · 24 OpenAI stories in the last 90 days
Follow OpenAI on Seventy →

Tap an underlined word to see what it means.

Read the original at OpenAI News

Something wrong in this story? Report a mistake. We check it against the source within 24 hours.

Share with your take

Start from our line and make it yours. It stays on your device until you post it.

Ask about this story

Answered only from this story, with the line it came from.