Related Models
Pricing
Input
$0.05
per 1M tokens
Output
$0.25
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 3.2 Instruct 3BQ:-0.1
$0.15+50%
Mistral LargeQ:+0.1
$3.00+2900%
Qwen3.5 0.8B (Non-reasoning)Q:+0.1
$0.02-80%
Qwen2.5 Coder 7B InstructQ:+0.2
$0.04-55%
Performance
109
tokens/sec
Faster than 58% of models
8.52
seconds
Faster than 14% of models
8.52
seconds
Faster than 43% of models
Market Median
94 tok/s
16% faster
Median TTFT
1.10s
671% slower
Throughput/Dollar
1089
tok/s per $/1M
Speed Comparison
GPT-5 (medium)
109 tok/s+0%
OpenAI: GPT-4o (2024-05-13)
108 tok/s-0%
Hy3-preview (Reasoning)
110 tok/s+1%
Benchmarks
MMLU-Pro
16.4%
GPQA Diamond
22.7%
HLE
5.8%
LiveCodeBench
0.2%
SciCode
0.0%
TerminalBench HardNot evaluated
MATH-500
5.9%
AIME
0.0%
AIME 2025Not evaluated
IFBenchNot evaluated
Long Context RecallNot evaluated
Tau2Not evaluated
Market AverageTop Score