We’ve improved prompt caching in the API for GPT-6, helping agents run faster and cost…
This is a dev post classified by Jev as Backend & APIs (a launch), kept by the Dev Radar because it carries real work, not commentary.
We’ve improved prompt caching in the API for GPT-6, helping agents run faster and cost less. Higher cache-hit rates by default mean more input tokens benefit from cached-input discounts of up to 90%.
Posted by OpenAI Developers (431.7k followers) 1 h ago · 178 likes · 8.3k views · view the original post on X. Kept by the Dev Radar as Backend & APIs.
More dev work like this
- i'm a simple man, whe i see a connector that needs Google Cloud menu navigation (like… — @theaaron
- I am cooking up such a good launch video for social sdk 🥹 — @leodev
- Excited to partner with @extruct_ai ! — @orthogonal_sh
- x402 v2 and MCP 2026-07-28 both moved routing and payment data into HTTP headers. That… — @AgenticAIFdn
- Excited to partner with @extruct_ai! — @orthogonal_sh
- x402 is the best when trying out new API services or completing one-off tasks via API… — @harpaljadeja
- Please welcome GPT-6 Sol and GPT-6 Luna to the GPT-6 universe. — @OpenAI
- GPT-6 Luna and Sol live on the API! — @cheatyyyy
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 21.5k posts from 5k X accounts over the last 21 days, 2.5k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-22 21:38 UTC. Full method.