OpenAI Adds Optional 12-Hour Prompt Caching to Its API

1 reports 1 reporting sources 2 hours agoNew

Understand the event

AI overview

OpenAI added an optional 12-hour prompt caching setting to its API, allowing developers to retain shared instructions, tools, and context for reuse across requests hours apart. OpenAI said requests that reuse the cached input can receive the lower cached-input rate. The company presented the longer caching window as useful for persistent agents that reuse context throughout the day.

Generated by AI from reports · Updated 1 hours ago

Latest development10/21 01:56 (UTC+8)

OpenAI adds optional 12-hour prompt caching in the API OpenAI Developers · X

Report timeline

Follow the reports to explore different sides of the event.

10/21

01:56
OpenAI Developers · X
OpenAI adds optional 12-hour prompt caching in the API
You can now choose 12-hour prompt caching in the API. Persistent agents, like dots, reuse context throughout the day. You can keep shared instructions, tools, and context cached longer and pay the lower cached-input rate, even when requests are hours apart.

The same kind of briefing as the one above: a few stories worth reading. Free. Mail starts after you confirm, and every letter has a one-click unsubscribe. Read a past issue

Event heat trend

There is not enough continuous observation data to plot a trend yet.

Keep reading

Latest daily · Issue 27TorchNeuron brings native PyTorch support for Hugging Face models on AWS Trainium