No longer supported
This model is legacy (released February 2024) and is no longer actively maintained or recommended by Google. Consider using their current flagship model instead.
by Google· Released February 2024· Cutoff Early 2023
Gemini 1.0 Nano is the smallest and most efficient model in the Gemini 1.0 series, designed for on-device and latency-sensitive applications. It offers strong performance for tasks like summarization, classification, and extraction while being optimized for mobile and edge devices. As a legacy model, it has been succeeded by more capable versions like Gemini 1.5 Flash.
Input cost
Free (limited) or $0.15 per 1M tokens
Output cost
Free (limited) or $0.60 per 1M tokens
Context window
32K tokens
Max output
2048 tokens
Modalities
License
proprietary
On-device and low-latency text tasks where efficiency is critical.
