Gemini 2.5 Flash
Fast, cost-efficient thinking model
Google DeepMind's Gemini 2.5 Flash is a multimodal model release optimized for fast, cost-efficient reasoning and high-throughput use cases.
Pricing
Model profile · Current snapshot
Input / 1M
$0.10
Output / 1M
$0.40
Blended / 1M
$0.175
Output TPS
225
TTFT (s)
0.32
Model Intelligence
Context window
1,048,576 tokens
Arena ranking
7
Benchmarkable
Yes
Model level
release
Intelligence Index
14.1
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
0.46
TerminalBench Hard
0.12
TAU2
0.15
Recent stories
0 linked stories
No linked stories yet.