Gemini 2.5 Flash

a year ago

Gemini 2.5 Flash is now available in preview via the Gemini API in Google AI Studio and Vertex AI.
It is a hybrid reasoning model, allowing developers to toggle reasoning capabilities on or off.
Developers can set a thinking budget to balance quality, cost, and latency.
The model automatically adjusts its reasoning based on task complexity.
Gemini 2.5 Flash offers improved performance over 2.0 Flash, even with reasoning turned off.
The thinking budget can range from 0 to 24576 tokens.
The model excels in complex tasks requiring multi-step reasoning.
Example use cases include solving math problems, scheduling, and spreadsheet calculations.
Pricing details are sourced from Artificial Analysis & Company Documentation.

Hasty Briefsbeta