Gemini 2.5 Flash
Our best model in terms of price-performance, offering well-rounded capabilities.
Gemini 2.5 Flash is a stable Gemini API model release in the Gemini 2.5 thinking model family, optimized for price-performance, low-latency/high-volume processing, reasoning, and agentic use cases. The official model code is gemini-2.5-flash; it accepts text, image, video, and audio inputs and outputs text.
Pricing
Model profile · Current snapshot
Input / 1M
$0.30
Output / 1M
$2.50
Blended / 1M
$0.85
Output TPS
0
TTFT (s)
0
Model Intelligence
Context window
1,048,576 tokens
Arena ranking
14
Benchmarkable
Yes
Model level
release
Intelligence Index
14.2
Math Index
60.3
MMLU Pro
0.81
GPQA
0.68
HLE
0.05
LiveCodeBench
0.5
SciCode
0.29
MATH-500
0.93
AIME
0.5
AIME 2025
0.6
IFBench
0.39
LCR
0.48
TerminalBench Hard
0.12
TAU2
0.15
Recent stories
0 linked stories
No linked stories yet.