💬
gemini-2.5-flash-lite
openrouter
Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models. By default, "thinking" (i.e. multi-pass reasoning) is disabled to prioritize speed, but developers can enable it via the Reasoning API parameter to selectively trade off cost for intelligence.
Model Type
chat
Cost
20 tokens / 1_megabitpixiels
Features
Stream
Model Settings
image size
portrait_16_9, square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9
num images
4, 3, 2, 1
num inference steps
12, 1, 4, 8
enable safety checker
false, true
Join the Discussion
Have questions or want to share your experience with gemini-2.5-flash-lite? Join the conversation in our forums.
Visit Forums