Related Models
Pricing
Input
$0.05
per 1M tokens
Output
$0.40
per 1M tokens
Blended
$0.14
per 1M tokens
Cheaper than 78% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.14
Monthly
$4.14
vs. Similar Models
Olmo 3.1 32B ThinkQ:+0.1
$0.24+72%
Pixtral LargeQ:+0.1
$3.00+2074%
OpenAI: GPT-4 TurboQ:-0.1
$15.00+10770%
Ring-flash-2.0Q:+0.2
$0.25+79%
Performance
149
tokens/sec
Faster than 74% of models
0.67
seconds
Faster than 72% of models
0.67
seconds
Faster than 80% of models
Market Median
94 tok/s
59% faster
Median TTFT
1.10s
39% faster
Throughput/Dollar
1077
tok/s per $/1M
Speed Comparison
Mistral Small 4 (Non-reasoning)
149 tok/s+0%
Qwen: Qwen3.5-122B-A10B
148 tok/s-0%
Apertus 8B Instruct
148 tok/s-0%
Benchmarks
MMLU-Pro
55.6%
GPQA Diamond
42.8%
HLE
4.1%
LiveCodeBench
47.0%
SciCode
29.1%
TerminalBench Hard
6.8%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025
27.3%
IFBench
32.5%
Long Context Recall
20.0%
Tau2
25.7%
Market AverageTop Score