Gemini 2.5 Flash-Lite (Reasoning)

Google·Released 2025-06-17

Compare

Quality Index

17.6

223rd of 440

Top 51%

Coding Index

9.5

271st of 350

Top 78%

Math Index

53.3

134th of 268

Top 50%

Price/1M

$0.17

277th cheapest

44% below median

Top 42%

Speed

271 tok/s

Top 3%

TTFT

22.38s

Market Position

Gemini 2.5 Flash-Lite (Reasoning)Market Average

Pricing

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.

Cost Calculator

Tokens per day1M

100K100M

Daily

$0.17

Monthly

$5.25

vs. Similar Models

Hermes 4 - Llama-3.1 405B (Non-reasoning)Q:0.0

$1.50+757%

Gemini 2.5 Flash Preview (Non-reasoning)Q:+0.2

$0.00-100%

Llama 3.1 Instruct 405BQ:-0.2

$3.69+2007%

Sonar ReasoningQ:+0.3

$0.00-100%

Performance

271

tokens/sec

Faster than 97% of models

22.38

seconds

Faster than 4% of models

Market Median

46 tok/s

491% faster

Median TTFT

0.43s

5106% slower

Throughput/Dollar

1549

tok/s per $/1M

Speed Comparison

GPT-5.4 mini (medium)

270 tok/s-0%

gpt-oss-120B (low)

273 tok/s+1%

gpt oss 120b

277 tok/s+2%

Benchmarks

MMLU-Pro

75.9%

GPQA Diamond

62.5%

HLE

6.4%

LiveCodeBench

59.3%

SciCode

19.3%

TerminalBench Hard

4.5%

MATH-500

96.9%

AIME

70.3%

AIME 2025

53.3%

IFBench

49.9%

Long Context Recall

51.3%

Tau2

18.4%

Market AverageTop Score

Quick Compare

Similar Models

Hermes 4 - Llama-3.1 405B (Non-reasoning)

Nous Research

Q: 17.6$1.50/1M

Slower: 89%Pricier: 757%

Gemini 2.5 Flash Preview (Non-reasoning)

Google

Q: 17.8$0.00/1M

Slower: 100%Cheaper: 100%

Llama 3.1 Instruct 405B