Related Models
Pricing
Input
$0.70
per 1M tokens
Output
$8.40
per 1M tokens
Blended
$2.63
per 1M tokens
Cheaper than 23% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$2.63
Monthly
$78.75
vs. Similar Models
QwQ 32BQ:0.0
$0.74-72%
Qwen3 VL 30B A3B (Reasoning)Q:-0.1
$0.34-87%
Qwen: Qwen3 Coder 30B A3B InstructQ:+0.2
$0.12-95%
Gemma 4 12B (Non-reasoning)Q:-0.2
$0.15-94%
Performance
66
tokens/sec
Faster than 33% of models
1.22
seconds
Faster than 43% of models
31.42
seconds
Faster than 16% of models
Market Median
94 tok/s
30% slower
Median TTFT
1.11s
10% slower
Throughput/Dollar
25
tok/s per $/1M
Speed Comparison
GPT-5 (minimal)
66 tok/s-0%
inclusionAI: Ling-2.6-1T
67 tok/s+1%
GPT-5.5 (Non-reasoning)
66 tok/s-1%
Benchmarks
MMLU-Pro
82.8%
GPQA Diamond
70.0%
HLE
11.7%
LiveCodeBench
62.2%
SciCode
39.9%
TerminalBench Hard
6.1%
MATH-500
93.0%
AIME
84.0%
AIME 2025
82.0%
IFBench
38.7%
Long Context Recall
0.0%
Tau2
24.0%
Market AverageTop Score