Loading...
About
GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...
Related Models
Pricing
Input
$0.13
per 1M tokens
Output
$0.85
per 1M tokens
Blended
$0.31
per 1M tokens
Cheaper than 61% of models. Median price is $0.56/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.31
Monthly
$9.30
vs. Similar Models
Nova 2.0 Omni (low)Q:0.0
$0.85+174%
Nova 2.0 Pro Preview (Non-reasoning)Q:-0.1
$3.44+1009%
xAI: Grok 4 FastQ:-0.1
$0.28-11%
GPT-5.4 mini (Non-Reasoning)Q:+0.1
$1.69+445%
Performance
67
tokens/sec
Faster than 36% of models
1.43
seconds
Faster than 34% of models
31.31
seconds
Faster than 14% of models
Market Median
86 tok/s
22% slower
Median TTFT
1.07s
34% slower
Throughput/Dollar
216
tok/s per $/1M
Speed Comparison
GPT-5.5 (high)
67 tok/s-0%
inclusionAI: Ling-2.6-1T
67 tok/s-1%
Qwen: Qwen-Turbo
67 tok/s+1%
Context Window
131K
tokens
Larger than 33% of models
Max Output
98K
tokens
75% of context
Benchmarks
MMLU-Pro
81.5%
GPQA Diamond
73.3%
HLE
6.8%
LiveCodeBench
68.4%
SciCode
30.6%
TerminalBench Hard
20.5%
MATH-500
96.5%
AIME
67.3%
AIME 2025
80.7%
IFBench
37.6%
Long Context Recall
43.7%
Tau2
46.5%
Market AverageTop Score