Related Models
Pricing
Input
$0.25
per 1M tokens
Output
$0.97
per 1M tokens
Blended
$0.43
per 1M tokens
Cheaper than 54% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.43
Monthly
$12.90
vs. Similar Models
GPT-4o (Aug '24)Q:0.0
$4.38+917%
Qwen2.5 Instruct 72BQ:0.0
$0.37-14%
Ling-flash-2.0Q:+0.1
$0.25-43%
Perplexity: SonarQ:-0.1
$1.00+133%
Performance
102
tokens/sec
Faster than 55% of models
0.95
seconds
Faster than 59% of models
20.64
seconds
Faster than 24% of models
Market Median
94 tok/s
8% faster
Median TTFT
1.10s
14% faster
Throughput/Dollar
236
tok/s per $/1M
Speed Comparison
GPT-5 mini (medium)
102 tok/s-0%
Z.ai: GLM 4.7 Flash
102 tok/s+1%
Llama 3.2 Instruct 11B (Vision)
101 tok/s-1%
Benchmarks
MMLU-Pro
79.2%
GPQA Diamond
72.6%
HLE
7.3%
LiveCodeBench
67.9%
SciCode
30.6%
TerminalBench Hard
3.8%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025
74.0%
IFBench
43.4%
Long Context Recall
0.0%
Tau2
21.3%
Market AverageTop Score