Model Comparison
DeepSeek-V4-Pro
vs
GLM-4.6V
May 11, 2026
Pricing
Input
$
1.74
/ M Tokens
$
0.3
/ M Tokens
Output
$
3.48
/ M Tokens
$
0.9
/ M Tokens
Metadata
Specification
State
Available
Available
Architecture
Hybrid Attention MoE
Multimodal MoE
Calibrated
Yes
Yes
Mixture of Experts
Yes
Yes
Total Parameters
862B
106B
Activated Parameters
49B
106B
Reasoning
No
No
Precision
FP8
FP8
Context length
1049K
131K
Max Tokens
393K
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
Supported
Not supported
Structured Outputs
Not supported
Not supported
Tools
Supported
Supported
Fim Completion
Not supported
Not supported
Chat Prefix Completion
Supported
Not supported
DeepSeek-V4-Pro in Comparison
See how DeepSeek-V4-Pro compares with other popular models across key dimensions.
