Related Models
Pricing
Input
$2.50
per 1M tokens
Output
$10.00
per 1M tokens
Blended
$4.38
per 1M tokens
Cheaper than 13% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$4.38
Monthly
$131.25
vs. Similar Models
Qwen2.5 Instruct 72BQ:0.0
$0.37-92%
Qwen3 Omni 30B A3B (Reasoning)Q:0.0
$0.43-90%
Ling-flash-2.0Q:+0.1
$0.25-94%
Perplexity: SonarQ:-0.1
$1.00-77%
Performance
121
tokens/sec
Faster than 64% of models
0.60
seconds
Faster than 78% of models
0.60
seconds
Faster than 85% of models
Market Median
94 tok/s
29% faster
Median TTFT
1.10s
46% faster
Throughput/Dollar
28
tok/s per $/1M
Speed Comparison
Qwen: Qwen3 VL 30B A3B Instruct
121 tok/s-0%
Nex AGI: Nex-N2-Pro
121 tok/s-0%
Grok 4.3 (Non-reasoning)
121 tok/s-0%
Context Window
128K
tokens
Larger than 16% of models
Max Output
16K
tokens
13% of context
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
52.1%
HLE
2.9%
LiveCodeBench
31.7%
SciCode
33.1%
TerminalBench Hard
8.3%
MATH-500
79.5%
AIME
11.7%
AIME 2025Not evaluated
IFBench
36.0%
Long Context Recall
35.0%
Tau2
28.9%
Market AverageTop Score