Back to Explore
Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)
Google·Released 2025-09-08
MoEMultimodal
Related Models
Google: Gemini 3.5 Flash2026-05-19Gemini 3.5 Flash (medium)2026-05-19Gemini 3.5 Flash (minimal)2026-05-19Google: Gemini 3.1 Flash Lite2026-05-07Google: Gemini 3.1 Flash Lite Preview2026-03-03Google: Gemini 3.1 Pro Preview Custom Tools2026-02-25Google: Gemini 3.1 Pro Preview2026-02-19Gemini 3 Deep Think2026-02-05
Pricing
Input
$0.10
per 1M tokens
Output
$0.40
per 1M tokens
Blended
$0.17
per 1M tokens
Cheaper than 72% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.17
Monthly
$5.25
vs. Similar Models
OpenAI: gpt-oss-20bQ:-0.2
$0.06-68%
Nemotron 3 Nano Omni 30B A3B ReasoningQ:-0.2
$0.13-25%
GPT-5 (ChatGPT)Q:+0.2
$3.44+1865%
Mistral: Mistral Medium 3.1Q:-0.3
$0.80+357%
Performance
347
tokens/sec
Faster than 97% of models
13.81
seconds
Faster than 9% of models
13.81
seconds
Faster than 34% of models
Market Median
94 tok/s
268% faster
Median TTFT
1.11s
1140% slower
Throughput/Dollar
1982
tok/s per $/1M
Speed Comparison
gpt-oss-120b (low)
340 tok/s-2%
Google: Gemini 2.5 Flash Lite Preview 09-2025
353 tok/s+2%
LFM2 2.6B
335 tok/s-3%
Benchmarks
MMLU-Pro
80.8%
GPQA Diamond
70.9%
HLE
6.6%
LiveCodeBench
68.8%
SciCode
28.7%
TerminalBench Hard
12.9%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025
68.7%
IFBench
52.6%
Long Context Recall
59.0%
Tau2
30.7%
Market AverageTop Score