Loading...
Loading...
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](https://openrouter.ai/docs/use-cases/reasoning-tokens) to selectively trade off cost for intelligence.
Quality Index
12.7
312th of 442
Top 71%
Coding Index
7.4
290th of 352
Top 83%
Math Index
35.3
172nd of 268
Top 65%
Price/1M
$0.17
277th cheapest
44% below median
Top 42%
Speed
244 tok/s
Top 3%
TTFT
0.34s
Context Window
1.0M
8th largest
Top 6%
Input
$0.10
per 1M tokens
Output
$0.40
per 1M tokens
Blended
$0.17
per 1M tokens
Cheaper than 58% of models. Median price is $0.31/1M tokens.
Daily
$0.17
Monthly
$5.25
244
tokens/sec
Faster than 97% of models
0.34
seconds
Faster than 57% of models
0.34
seconds
Faster than 58% of models
Market Median
46 tok/s
435% faster
Median TTFT
0.42s
20% faster
Throughput/Dollar
1395
tok/s per $/1M
Speed Comparison
Context Window
1.0M
tokens
Larger than 94% of models
Max Output
66K
tokens
6% of context