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
Grok 4Q:+0.1
$11.00+7233%
Gemini 3 Pro Preview (low)Q:-0.1
$4.50+2900%
DeepSeek V3.2 (Reasoning)Q:+0.2
$0.34+125%
OpenAI: GPT-5 MiniQ:-0.2
$0.69+358%
Performance
92
tokens/sec
Faster than 49% of models
1.76
seconds
Faster than 27% of models
23.51
seconds
Faster than 21% of models
Market Median
95 tok/s
3% slower
Median TTFT
1.11s
59% slower
Throughput/Dollar
613
tok/s per $/1M
Speed Comparison
Hermes 4 - Llama-3.1 70B (Reasoning)
91 tok/s-1%
MiMo-V2-Flash (Non-reasoning)
93 tok/s+1%
Hermes 4 - Llama-3.1 70B (Non-reasoning)
91 tok/s-1%
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
83.5%
HLE
20.0%
LiveCodeBenchNot evaluated
SciCode
38.3%
TerminalBench Hard
31.1%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
71.8%
Long Context Recall
64.3%
Tau2
93.3%
Market AverageTop Score