Box Developer Documentation

Google Gemini 2.5 Flash Preview

Guides Box AI Supported AI models Google Gemini 2.5 Flash Preview
Edit this page

Google Gemini 2.5 Flash Preview

Google Gemini 2.5 Flash Preview is a multimodal model designed to handle lightweight tasks. It is designed for high-volume, low-latency tasks, making it highly efficient for large-scale use cases like summarization, multimodal processing, and categorization but with higher quality than Gemini 2.0 Flash.

Model details

ItemValueDescription
Model nameGoogle Gemini 2.5 Flash PreviewThe name of the model.
API model namegoogle__gemini_2_5_flash_previewThe name of the model that is used in the Box AI API for model overrides. The user must provide this exact name for the API to work.
Hosting layerGoogleThe trusted organization that securely hosts LLM.
Model providerGoogleThe organization that provides this model.
Release dateMarch 25th 2025The release date for the model.
Knowledge cutoff dateJanuary 2025The date after which the model does not get any information updates.
Input context window1m tokensThe number of tokens supported by the input context window.
Maximum output tokens8k tokensThe number of tokens that can be generated by the model in a single request.
Empirical throughput214The number of tokens the model can generate per second.
Open sourceNoSpecifies if the model's code is available for public use.

Additional documentation

For additional information, see official Google Gemini 2.5 Flash Preview documentation.