Google has announced the availability of context caching for its Gemini 1.5 Pro and 1.5 Flash models. This feature is designed to enhance long-context scenarios by allowing developers to cache millions of tokens, making it easier to reference large initial inputs with shorter subsequent requests. The new context caching capability is now twice as affordable as previously announced, providing significant cost savings for developers. This development is particularly beneficial for AI applications that require extensive data referencing, and the feature is available immediately. TPUs are particularly well-suited for this feature by design. The announcement was made on June 18, 2024.
The context caching feature for Gemini is really neat! As you all know, I write a lot and document AI research progress in lots of places. But I also tend to forget research findings due to the vast amount of papers I read so I wanted to try whether context caching can help me⦠https://t.co/7Q7G2RapFD
The context caching feature for Gemini is really neat! As you all know, I write a lot and document AI research progress in lots of places. But I also tend to forget research findings due to the vast amount of papers I read so I wanted to try whether context caching can help me⦠https://t.co/EGPzweGvdd
Context caching is actually quite a big deal, its something TPUs are very good at by design. https://t.co/QteJ97OHhg
πΎ Context caching is here for our Gemini 1.5 models! Context caching is particularly well suited to long-context scenarios where an initial large input is referenced repeatedly by shorter requests. Gemini gives you the ability to cache millions of tokens to inform your outputs!β¦ https://t.co/Q6rIflBLLU
WOW. Google is making promises and shipping! I'm super excited to try out context caching, especially as we're building complex AI assistants. https://t.co/d8ycM7r8y9
Great news for @Google developers: Context caching for the Gemini API is here, supports both 1.5 Flash and 1.5 Pro, is 2x cheaper than we previously announced, and is available to everyone right now. π€― https://t.co/jLHHaqRsfD
Context caching is now available for Gemini 1.5 Pro and 1.5 Flash! π At a lower cost, context caching in the Gemini API makes working with millions of tokens a breeze. Pass content once, cache the tokens, and refer back for later requests. Learn more β https://t.co/uNZw50KbpY https://t.co/hhBPeICV8n