Hub/Models/google/gemini-2.5-flash-lite
googletext + image + file + audio + video → text

Google: Gemini 2.5 Flash Lite

Canonical ID: google/gemini-2.5-flash-lite

Compare ModelOpen on 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...

Artificial Analysis Benchmarks

Verified
No standardized Artificial Analysis benchmark scores recorded for this variant yet.

Token Pricing & Economics

Prompt Input (1M Tokens)
$0.10
Input
Completion Output (1M Tokens)
$0.40
Output
Prompt KV-Cache Read (1M Tokens)
$0.01
Cached
Context Window Capacity
1,024k tokens
Context

Supported Parameters & Features

include_reasoningmax_tokensreasoningresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p