Related Models
Pricing
Input
$0.11
per 1M tokens
Output
$1.26
per 1M tokens
Blended
$0.40
per 1M tokens
Cheaper than 56% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.40
Monthly
$11.94
vs. Similar Models
Gemma 3n E4B InstructQ:-0.1
$0.03-94%
Llama 3 Instruct 8BQ:-0.1
$0.07-82%
Qwen3 1.7B (Non-reasoning)Q:+0.2
$0.19-53%
Gemma 3 4B InstructQ:-0.2
$0.05-87%
Performance
224
tokens/sec
Faster than 92% of models
1.19
seconds
Faster than 45% of models
10.13
seconds
Faster than 40% of models
Market Median
94 tok/s
139% faster
Median TTFT
1.10s
8% slower
Throughput/Dollar
562
tok/s per $/1M
Speed Comparison
Gemini 2.5 Flash (Reasoning)
224 tok/s-0%
Qwen3 0.6B (Non-reasoning)
222 tok/s-1%
Google: Gemini 2.5 Flash
226 tok/s+1%
Benchmarks
MMLU-Pro
34.7%
GPQA Diamond
23.9%
HLE
5.7%
LiveCodeBench
12.1%
SciCode
2.8%
TerminalBench Hard
0.0%
MATH-500
75.0%
AIME
10.0%
AIME 2025
18.0%
IFBench
23.3%
Long Context Recall
0.0%
Tau2
21.1%
Market AverageTop Score