Related Models
Pricing
Input
$0.11
per 1M tokens
Output
$1.26
per 1M tokens
Blended
$0.40
per 1M tokens
Cheaper than 56% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.40
Monthly
$11.94
vs. Similar Models
Qwen3 VL 8B InstructQ:0.0
$0.18-54%
Llama 3.1 Instruct 405BQ:+0.1
$3.69+827%
Claude 3.5 Sonnet (June '24)Q:-0.1
$6.00+1408%
Llama 3.3 Instruct 70BQ:+0.2
$0.61+54%
Performance
104
tokens/sec
Faster than 56% of models
1.13
seconds
Faster than 47% of models
20.35
seconds
Faster than 25% of models
Market Median
94 tok/s
11% faster
Median TTFT
1.10s
3% slower
Throughput/Dollar
262
tok/s per $/1M
Speed Comparison
Qwen3 4B (Non-reasoning)
104 tok/s+0%
GPT-5 mini (minimal)
103 tok/s-1%
Claude 4.5 Haiku (Non-reasoning)
103 tok/s-1%
Benchmarks
MMLU-Pro
69.6%
GPQA Diamond
52.2%
HLE
5.1%
LiveCodeBench
46.5%
SciCode
3.5%
TerminalBench HardNot evaluated
MATH-500
93.3%
AIME
65.7%
AIME 2025
22.3%
IFBench
32.5%
Long Context Recall
0.0%
Tau2
19.0%
Market AverageTop Score