Related Models
Google: Gemini 3.5 Flash2026-05-19Gemini 3.5 Flash (medium)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 Think2026-02-05Gemini 3 Flash Preview (Reasoning)2025-12-17
Pricing
Input
$1.50
per 1M tokens
Output
$9.00
per 1M tokens
Blended
$3.38
per 1M tokens
Cheaper than 22% of models. Median price is $0.67/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$3.38
Monthly
$101.25
vs. Similar Models
MiMo-V2-OmniQ:+0.1
$0.80-76%
Anthropic: Claude Opus 4.5Q:-0.2
$10.00+196%
OpenAI: GPT-5Q:-0.2
$3.44+2%
OpenAI: GPT-5.1-CodexQ:-0.2
$3.44+2%
Performance
216
tokens/sec
Faster than 90% of models
0.73
seconds
Faster than 70% of models
0.73
seconds
Faster than 78% of models
Market Median
93 tok/s
132% faster
Median TTFT
1.13s
35% faster
Throughput/Dollar
64
tok/s per $/1M
Speed Comparison
GPT-5.6 Luna (high)
217 tok/s+0%
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)
215 tok/s-0%
Google: Gemini 2.5 Flash Lite
215 tok/s-1%
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
82.8%
HLE
23.1%
LiveCodeBenchNot evaluated
SciCode
48.8%
TerminalBench Hard
46.2%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
47.3%
Long Context Recall
53.3%
Tau2
58.8%
Market AverageTop Score