Related Models
Pricing
Input
$0.10
per 1M tokens
Output
$0.10
per 1M tokens
Blended
$0.10
per 1M tokens
Cheaper than 83% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.10
Monthly
$3.00
vs. Similar Models
Llama 3.1 Instruct 70BQ:0.0
$0.56+460%
Qwen3 30B A3B (Non-reasoning)Q:0.0
$0.13+33%
Qwen3 4B (Non-reasoning)Q:0.0
$0.19+88%
IBM: Granite 4.1 8BQ:-0.1
$0.06-38%
Performance
168
tokens/sec
Faster than 80% of models
0.43
seconds
Faster than 93% of models
0.43
seconds
Faster than 95% of models
Market Median
94 tok/s
78% faster
Median TTFT
1.11s
61% faster
Throughput/Dollar
1676
tok/s per $/1M
Speed Comparison
OpenAI: GPT-5.4
166 tok/s-1%
Qwen3 30B A3B 2507 Instruct
166 tok/s-1%
Llama 3.1 Instruct 8B
171 tok/s+2%
Benchmarks
MMLU-Pro
52.4%
GPQA Diamond
35.8%
HLE
5.3%
LiveCodeBench
24.7%
SciCode
14.4%
TerminalBench Hard
0.0%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025
22.0%
IFBench
26.8%
Long Context Recall
11.7%
Tau2
24.9%
Market AverageTop Score