Loading...
About
Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...
Related Models
Google: 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 Think2026-02-05Gemini 3 Flash Preview (Reasoning)2025-12-17Gemini 3 Flash Preview (Non-reasoning)2025-12-17Google: Gemini 3 Flash Preview2025-12-17
Pricing
Input
$0.10
per 1M tokens
Output
$0.40
per 1M tokens
Blended
$0.17
per 1M tokens
Cheaper than 73% of models. Median price is $0.56/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.17
Monthly
$5.25
vs. Similar Models
Mistral Small 3Q:0.0
$0.10-41%
Nova LiteQ:0.0
$0.10-40%
Z.ai: GLM 4.5VQ:0.0
$0.90+414%
Hermes 4 - Llama-3.1 70B (Non-reasoning)Q:-0.1
$0.20+13%
Performance
259
tokens/sec
Faster than 95% of models
1.28
seconds
Faster than 38% of models
1.28
seconds
Faster than 58% of models
Market Median
86 tok/s
202% faster
Median TTFT
1.07s
19% slower
Throughput/Dollar
1480
tok/s per $/1M
Speed Comparison
gpt-oss-120B (low)
254 tok/s-2%
OpenAI: gpt-oss-120b
244 tok/s-6%
Qwen3.5 Omni Flash
244 tok/s-6%
Context Window
1.0M
tokens
Larger than 91% of models
Max Output
66K
tokens
6% of context
Benchmarks
MMLU-Pro
72.4%
GPQA Diamond
47.4%
HLE
3.7%
LiveCodeBench
40.0%
SciCode
17.7%
TerminalBench Hard
2.3%
MATH-500
92.6%
AIME
50.0%
AIME 2025
35.3%
IFBench
31.5%
Long Context Recall
31.3%
Tau2
19.0%
Market AverageTop Score
