OpenAI credits caching and inference gains for GPT-6's 50% price cut

OpenAIDevs · x · 2026-09-23

OpenAI Devs explained GPT-6 Sol and Luna's lower prices come from caching and inference improvements, passing savings on: more intelligence at half the previous generation's API prices, making complex automation practical at scale.

Related event: OpenAI Launches GPT-6 Sol and Luna with 50% API Price Cut(6 posts)→

Original post →

More from Infra

Infra channel →