Related Models
Pricing
Input
$0.02
per 1M tokens
Output
$0.04
per 1M tokens
Blended
$0.03
per 1M tokens
Cheaper than 91% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.03
Monthly
$0.75
vs. Similar Models
Llama 3 Instruct 8BQ:0.0
$0.07+180%
Gemma 3 4B InstructQ:-0.1
$0.05+100%
Llama 3.2 Instruct 1BQ:-0.1
$0.05+100%
Qwen3 0.6B (Reasoning)Q:+0.1
$0.40+1492%
Performance
50
tokens/sec
Faster than 17% of models
0.55
seconds
Faster than 82% of models
0.55
seconds
Faster than 88% of models
Market Median
94 tok/s
46% slower
Median TTFT
1.10s
50% faster
Throughput/Dollar
2010
tok/s per $/1M
Speed Comparison
Z.ai: GLM 4.5V
50 tok/s+0%
GLM-4.6V (Reasoning)
50 tok/s+0%
GLM-4.6 (Reasoning)
50 tok/s-0%
Benchmarks
MMLU-Pro
48.8%
GPQA Diamond
29.6%
HLE
4.4%
LiveCodeBench
14.6%
SciCode
8.1%
TerminalBench Hard
2.3%
MATH-500
77.1%
AIME
13.7%
AIME 2025
14.3%
IFBench
27.9%
Long Context Recall
0.0%
Tau2
5.0%
Market AverageTop Score