Just weeks after unveiling Gemini 2.5 Pro, Google is on to its next top-performing model. On Thursday, the company released an "early version" of Gemini 2.5 Flash in preview in the Gemini API, AI ...

TL;DR Key Takeaways : Gemini AI’s new implicit caching feature reduces token costs by up to 75% for its 2.5 reasoning models by automatically applying discounts for repeated prompt prefixes.

For prompts up to 200,000 tokens, Gemini 2.5 Pro costs $1.25 per million input tokens (roughly 750,000 words, longer than the entire “Lord of The Rings” series) and $10 per million output tokens.

In contrast to explicit caching, implicit caching is automatic. Enabled by default for Gemini 2.5 models, it passes on cost savings if a Gemini API request to a model hits a cache.

Google's Veo 3 model is now accessible via the Gemini API, enabling developers to generate videos at $0.75 per second. The model supports 720p resolution and includes AI audio, with a faster ...