Related Models
Pricing
Input
$0.06
per 1M tokens
Output
$0.24
per 1M tokens
Blended
$0.10
per 1M tokens
Cheaper than 82% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.10
Monthly
$3.15
vs. Similar Models
Google: Gemini 2.5 Flash LiteQ:0.0
$0.17+67%
Hermes 4 - Llama-3.1 70B (Non-reasoning)Q:0.0
$0.20+89%
Mistral Small 3Q:0.0
$0.10-1%
OpenAI: GPT-4o-miniQ:0.0
$0.26+150%
Performance
166
tokens/sec
Faster than 80% of models
0.65
seconds
Faster than 73% of models
0.65
seconds
Faster than 81% of models
Market Median
94 tok/s
78% faster
Median TTFT
1.10s
41% faster
Throughput/Dollar
1583
tok/s per $/1M
Speed Comparison
Nemotron 3 Ultra 550B A55B (Reasoning)
166 tok/s-0%
Gemma 4 12B (Non-reasoning)
167 tok/s+0%
Command A+
167 tok/s+0%
Benchmarks
MMLU-Pro
59.0%
GPQA Diamond
43.3%
HLE
4.6%
LiveCodeBench
16.7%
SciCode
13.9%
TerminalBench Hard
0.8%
MATH-500
76.5%
AIME
10.7%
AIME 2025
7.0%
IFBench
34.1%
Long Context Recall
17.7%
Tau2
17.5%
Market AverageTop Score