Related Models
Pricing
Input
$0.14
per 1M tokens
Output
$0.57
per 1M tokens
Blended
$0.25
per 1M tokens
Cheaper than 66% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.25
Monthly
$7.41
vs. Similar Models
Olmo 3.1 32B ThinkQ:-0.1
$0.24-4%
Pixtral LargeQ:-0.1
$3.00+1115%
Claude 3.5 Sonnet (June '24)Q:+0.1
$6.00+2329%
GPT-5 nano (minimal)Q:-0.2
$0.14-44%
Performance
86
tokens/sec
Faster than 46% of models
2.03
seconds
Faster than 22% of models
25.18
seconds
Faster than 20% of models
Market Median
94 tok/s
8% slower
Median TTFT
1.10s
84% slower
Throughput/Dollar
350
tok/s per $/1M
Speed Comparison
Llama 3.2 Instruct 1B
86 tok/s-0%
Llama 3.3 Instruct 70B
86 tok/s-1%
MiMo-V2-Omni
86 tok/s-1%
Benchmarks
MMLU-Pro
79.3%
GPQA Diamond
72.5%
HLE
8.9%
LiveCodeBench
62.8%
SciCode
16.8%
TerminalBench Hard
7.6%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025
83.7%
IFBench
43.3%
Long Context Recall
21.0%
Tau2
0.0%
Market AverageTop Score