Related Models
Pricing
Input
$0.15
per 1M tokens
Output
$0.59
per 1M tokens
Blended
$0.26
per 1M tokens
Cheaper than 66% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.26
Monthly
$7.80
vs. Similar Models
Llama 3.3 Instruct 70BQ:0.0
$0.61+135%
Mistral Small 3.1Q:0.0
$0.14-47%
OpenAI: GPT-4o (2024-05-13)Q:0.0
$7.50+2785%
Llama Nemotron Super 49B v1.5 (Non-reasoning)Q:+0.1
$0.17-33%
Performance
91
tokens/sec
Faster than 48% of models
1.33
seconds
Faster than 40% of models
1.33
seconds
Faster than 60% of models
Market Median
94 tok/s
3% slower
Median TTFT
1.10s
21% slower
Throughput/Dollar
350
tok/s per $/1M
Speed Comparison
Hermes 4 - Llama-3.1 70B (Non-reasoning)
90 tok/s-0%
Qwen3.5 27B (Non-reasoning)
90 tok/s-1%
Grok 4 Fast (Reasoning)
90 tok/s-1%
Benchmarks
MMLU-Pro
72.7%
GPQA Diamond
53.5%
HLE
4.3%
LiveCodeBench
28.8%
SciCode
28.0%
TerminalBench HardNot evaluated
MATH-500
86.9%
AIME
30.3%
AIME 2025
19.7%
IFBench
31.5%
Long Context Recall
0.0%
Tau2Not evaluated
Market AverageTop Score