Loading...
Loading...
Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling. Additionally, Gemini 2.5 Flash is configurable through the "max tokens for reasoning" parameter, as described in the documentation (https://openrouter.ai/docs/use-cases/reasoning-tokens#max-tokens-for-reasoning).
Quality Index
20.6
182nd of 442
Top 41%
Coding Index
17.8
165th of 352
Top 47%
Math Index
60.3
116th of 268
Top 43%
Price/1M
$0.85
450th cheapest
174% above median
Top 68%
Speed
209 tok/s
Top 6%
TTFT
0.41s
Context Window
1.0M
8th largest
Top 6%
Input
$0.30
per 1M tokens
Output
$2.50
per 1M tokens
Blended
$0.85
per 1M tokens
Cheaper than 32% of models. Median price is $0.31/1M tokens.
Daily
$0.85
Monthly
$25.50
209
tokens/sec
Faster than 94% of models
0.41
seconds
Faster than 51% of models
0.41
seconds
Faster than 53% of models
Market Median
46 tok/s
357% faster
Median TTFT
0.42s
2% faster
Throughput/Dollar
245
tok/s per $/1M
Speed Comparison
Context Window
1.0M
tokens
Larger than 94% of models
Max Output
66K
tokens
6% of context