Related Models
Pricing
Input
$0.65
per 1M tokens
Output
$2.75
per 1M tokens
Blended
$1.18
per 1M tokens
Cheaper than 33% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$1.18
Monthly
$35.25
vs. Similar Models
GPT-3.5 TurboQ:+0.1
$0.75-36%
Mistral MediumQ:+0.1
$4.09+248%
Mistral Small (Feb '24)Q:+0.1
$1.50+28%
Gemma 3 12B InstructQ:-0.1
$0.14-88%
Performance
47
tokens/sec
Faster than 13% of models
0.69
seconds
Faster than 72% of models
0.69
seconds
Faster than 80% of models
Market Median
95 tok/s
51% slower
Median TTFT
1.11s
38% faster
Throughput/Dollar
40
tok/s per $/1M
Speed Comparison
Microsoft: Phi 4 Mini Instruct
47 tok/s+0%
MoonshotAI: Kimi K2.6
46 tok/s-0%
Grok 4
47 tok/s+0%
Benchmarks
MMLU-Pro
57.4%
GPQA Diamond
37.9%
HLE
4.4%
LiveCodeBench
19.8%
SciCode
18.9%
TerminalBench Hard
0.8%
MATH-500
48.3%
AIME
0.0%
AIME 2025Not evaluated
IFBench
37.1%
Long Context Recall
0.0%
Tau2
0.0%
Market AverageTop Score