Skip to main content
Back to Explore

Google: Gemini 2.5 Flash

Google·Released 2025-06-17
1.0M ctxMoEMultimodal

About

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...

Pricing

Input

$0.30

per 1M tokens

Output

$2.50

per 1M tokens

Blended

$0.85

per 1M tokens

Cheaper than 39% of models. Median price is $0.54/1M tokens.

Cost Calculator

Tokens per day1M
100K100M

Daily

$0.85

Monthly

$25.50

vs. Similar Models

Upstage: Solar Pro 3Q:0.0
$0.26-69%
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)Q:+0.1
$0.10-89%
Qwen: Qwen3 VL 235B A22B InstructQ:+0.2
$0.37-56%
GPT-5 mini (minimal)Q:+0.2
$0.69-19%

Performance

226

tokens/sec

Faster than 92% of models

0.44

seconds

Faster than 93% of models

0.44

seconds

Faster than 95% of models

Market Median

94 tok/s

141% faster

Median TTFT

1.10s

60% faster

Throughput/Dollar

266

tok/s per $/1M

Speed Comparison

Google: Gemini 2.5 Flash Lite
227 tok/s+0%
Qwen3 0.6B (Reasoning)
224 tok/s-1%
Gemini 2.5 Flash (Reasoning)
224 tok/s-1%

Context Window

1.0M

tokens

Larger than 90% of models

Max Output

66K

tokens

6% of context

Benchmarks

MMLU-Pro
80.9%
GPQA Diamond
68.3%
HLE
5.1%
LiveCodeBench
49.5%
SciCode
29.1%
TerminalBench Hard
12.1%
MATH-500
93.2%
AIME
50.0%
AIME 2025
60.3%
IFBench
39.0%
Long Context Recall
45.9%
Tau2
14.9%
Market AverageTop Score

Quick Compare

Similar Models

Compare all 7 models