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
$0.50
per 1M tokens
Output
$3.00
per 1M tokens
Blended
$1.13
per 1M tokens
Cheaper than 34% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$1.13
Monthly
$33.75
vs. Similar Models
Anthropic: Claude Opus 4.6Q:0.0
$10.00+789%
Nemotron 3 Ultra 550B A55B (Reasoning)Q:0.0
$1.18+4%
xAI: Grok 4.3Q:-0.2
$1.56+39%
GPT-5.2 (medium)Q:+0.2
$4.81+328%
Performance
220
tokens/sec
Faster than 90% of models
5.81
seconds
Faster than 15% of models
5.81
seconds
Faster than 45% of models
Market Median
95 tok/s
132% faster
Median TTFT
1.11s
425% slower
Throughput/Dollar
195
tok/s per $/1M
Speed Comparison
Gemini 2.5 Flash (Reasoning)
219 tok/s-0%
MiniMax: MiniMax M2.1
220 tok/s+0%
Nova 2.0 Omni (Non-reasoning)
219 tok/s-0%
Benchmarks
MMLU-Pro
89.0%
GPQA Diamond
89.8%
HLE
34.7%
LiveCodeBench
90.8%
SciCode
50.6%
TerminalBench Hard
38.6%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025
97.0%
IFBench
78.0%
Long Context Recall
66.3%
Tau2
80.4%
Market AverageTop Score