Model Comparison
GLM-4.5-Air
vs
GLM-5
Feb 15, 2026
Pricing
Input
$
0.14
/ M Tokens
$
0.95
/ M Tokens
Output
$
0.86
/ M Tokens
$
2.55
/ M Tokens
Metadata
Specification
State
Available
Available
Architecture
GLM MoE
Sparse MoE
Calibrated
No
No
Mixture of Experts
Yes
Yes
Total Parameters
106B
750B
Activated Parameters
12B
40B
Reasoning
No
No
Precision
FP8
FP8
Context length
131K
205K
Max Tokens
131K
131K
Supported Functionality
Serverless
Supported
Supported
Serverless LoRA
Not supported
Not supported
Fine-tuning
Not supported
Not supported
Embeddings
Not supported
Not supported
Rerankers
Not supported
Not supported
Support image input
Not supported
Not supported
JSON Mode
Not supported
Not supported
Structured Outputs
Not supported
Not supported
Tools
Supported
Supported
Fim Completion
Not supported
Not supported
Chat Prefix Completion
Not supported
Not supported
GLM-4.5-Air in Comparison
See how GLM-4.5-Air compares with other popular models across key dimensions.
