Model Comparison
GLM-5
vs
Step-3.5-Flash
Feb 15, 2026
Pricing
Input
$
0.3
/ M Tokens
$
0.1
/ M Tokens
Output
$
2.55
/ M Tokens
$
0.3
/ M Tokens
Metadata
Create on
Feb 11, 2026
Feb 1, 2026
License
MIT
APACHE 2.0
Provider
Z.ai
StepFun
Specification
State
Available
Available
Architecture
Mixture of Experts (MoE) with DeepSeek Sparse Attention (DSA) and asynchronous RL stack
Sparse Mixture-of-Experts (MoE) transformer architecture
Calibrated
No
No
Mixture of Experts
Yes
Yes
Total Parameters
750B
196B
Activated Parameters
40B
11B
Reasoning
No
No
Precision
FP8
FP8
Context length
205K
262K
Max Tokens
131K
66K
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
Supported
GLM-5 in Comparison
See how GLM-5 compares with other popular models across key dimensions.
