Related Models
Pricing
Input
$0.20
per 1M tokens
Output
$1.25
per 1M tokens
Blended
$0.46
per 1M tokens
Cheaper than 52% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.46
Monthly
$13.89
vs. Similar Models
Google: Gemma 4 26B A4B Q:+0.1
$0.13-72%
OpenAI: o3Q:+0.2
$3.50+656%
Mistral: Mistral Medium 3.5Q:-0.3
$3.00+548%
GPT-5.4 mini (medium)Q:-0.4
$1.69+265%
Performance
156
tokens/sec
Faster than 76% of models
2.50
seconds
Faster than 20% of models
2.50
seconds
Faster than 50% of models
Market Median
94 tok/s
66% faster
Median TTFT
1.10s
126% slower
Throughput/Dollar
337
tok/s per $/1M
Speed Comparison
OpenAI: GPT-5.4
158 tok/s+2%
Nova 2.0 Pro Preview (Non-reasoning)
153 tok/s-2%
Ministral 3 3B
153 tok/s-2%
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
76.1%
HLE
14.7%
LiveCodeBenchNot evaluated
SciCode
38.4%
TerminalBench Hard
33.3%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
64.4%
Long Context Recall
57.3%
Tau2
52.6%
Market AverageTop Score