OpenAI discounts GPT-6 cached input up to 90%, if you reuse it inside 30 minutes

T2Covered by 1 source · first reported by UploadVR / Road to VR / MIXED at 27 Sept, 04:51 UTC

OpenAI has given the GPT-6 family a prompt caching system that discounts cached input tokens by up to 90%, for shared prefixes reused inside a 30-minute window. OpenAI said on September 22 that the discount applies to eligible shared prefixes, and that it comes with a caching dashboard and a…

aiiottelecomxr

Sources

• T2OpenAI discounts GPT-6 cached input up to 90%, if you reuse it inside 30 minutesUploadVR / Road to VR / MIXED27 Sept, 04:51