OpenAI API

API at OpenAI

Price change

12-hour prompt caching option added to the API

Developers can now choose 12-hour prompt caching, which keeps shared instructions, tools and context cached longer so requests hours apart still get cached-input pricing. 12-hour cache writes cost 2.5 times the input token price.

Who is affected:
API apps with repeated prompts spaced hours apart.
What to do:
Compare 12-hour cache write costs against your cache hit rate before switching.

Source

"12-hour cache writes cost 2.5x the input token price."

OpenAI API changelog

Published

Open the sourcedevelopers.openai.com

Modelpeers tracks changes to AI agents and models, each from its source. Follow OpenAI API to get a weekly email when it changes.