Related Models
Pricing
Input
$0.10
per 1M tokens
Output
$0.30
per 1M tokens
Blended
$0.15
per 1M tokens
Cheaper than 75% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.15
Monthly
$4.50
vs. Similar Models
DeepSeek V4 Pro (Non-reasoning)Q:0.0
$0.54+263%
GPT-5 (low)Q:0.0
$3.44+2192%
MiniMax: MiniMax M2.1Q:+0.2
$0.45+203%
Claude 4 Opus (Reasoning)Q:-0.2
$30.00+19900%
Performance
91
tokens/sec
Faster than 49% of models
1.85
seconds
Faster than 24% of models
23.82
seconds
Faster than 22% of models
Market Median
94 tok/s
4% slower
Median TTFT
1.11s
67% slower
Throughput/Dollar
607
tok/s per $/1M
Speed Comparison
Hermes 4 - Llama-3.1 70B (Non-reasoning)
91 tok/s-0%
Llama 3.3 Instruct 70B
92 tok/s+1%
Hermes 4 - Llama-3.1 70B (Reasoning)
90 tok/s-1%
Benchmarks
MMLU-Pro
84.3%
GPQA Diamond
84.6%
HLE
21.1%
LiveCodeBench
86.8%
SciCode
39.4%
TerminalBench Hard
28.0%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025
96.3%
IFBench
64.2%
Long Context Recall
63.0%
Tau2
95.0%
Market AverageTop Score