Google launches 'implicit caching' to make accessing its latest AI models cheaper | TechCrunch

"Implicit caching is a game-changer for developers using the Gemini API, offering automatic cost savings without manual configuration. It utilizes pre-computed responses for repetitive requests."

"The move to implicit caching upgrades previous explicit methods, aiming to alleviate the high costs developers faced while ensuring they benefit from automatic savings."

Google has launched a feature called 'implicit caching' in its Gemini API, significantly reducing costs for developers using Gemini 2.5 Pro and 2.5 Flash models. This feature enables automatic, substantial savings—up to 75%—when requests hit a cache by reusing previously computed data, unlike the manual and laborious explicit caching system that developers had to implement. The shift to implicit caching comes as a response to developer complaints about high API costs and is expected to make utilizing advanced AI models significantly more economical and efficient.

Read at TechCrunch