Related Models
Pricing
Input
$0.09
per 1M tokens
Output
$0.29
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
$4.20
vs. Similar Models
Llama 3 Instruct 70BQ:+0.1
$1.18+739%
Llama 3.2 Instruct 11B (Vision)Q:-0.1
$0.24+75%
GPT-3.5 TurboQ:+0.2
$0.75+436%
Mistral MediumQ:+0.2
$4.09+2820%
Performance
26
tokens/sec
Faster than 1% of models
3.95
seconds
Faster than 18% of models
3.95
seconds
Faster than 48% of models
Market Median
94 tok/s
72% slower
Median TTFT
1.10s
257% slower
Throughput/Dollar
185
tok/s per $/1M
Speed Comparison
MoonshotAI: Kimi K2 0905
26 tok/s-1%
MoonshotAI: Kimi K2 0711
26 tok/s+1%
Qwen3.5 2B (Non-reasoning)
27 tok/s+2%
Benchmarks
MMLU-Pro
59.5%
GPQA Diamond
34.9%
HLE
4.8%
LiveCodeBench
13.7%
SciCode
17.4%
TerminalBench Hard
0.8%
MATH-500
85.3%
AIME
22.0%
AIME 2025
18.3%
IFBench
36.7%
Long Context Recall
6.7%
Tau2
10.8%
Market AverageTop Score