← All models

Google: Gemini 2.5 Flash Lite Preview 09-2025

google/gemini-2.5-flash-lite-preview-09-2025

VisionTool useJSONReasoningStreaming

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...

Pricing

Input

$0.1 / 1M

Output

$0.4 / 1M

Specs

Context

1,048,576 tokens

Input

text, image, file, audio, video

Output

text

Knowledge cutoff: 2025-01-31

Released: 2025-09

Supported parameters

include_reasoningmax_tokensreasoningresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p