Model Comparison
DeepSeek-V3.2-Exp
vs
MiniMax-M1-80k
Jan 13, 2026
Pricing
Input
$
0.27
/ M Tokens
$
0.55
/ M Tokens
Output
$
0.41
/ M Tokens
$
2.2
/ M Tokens
Metadata
Create on
Sep 29, 2025
Jun 13, 2025
License
MIT
APACHE-2.0
Provider
DeepSeek
MiniMaxAI
Specification
State
Available
Available
Architecture
Calibrated
No
Yes
Mixture of Experts
No
Yes
Total Parameters
671B
456B
Activated Parameters
45.9B
Reasoning
No
No
Precision
FP8
FP8
Context length
164K
131K
Max Tokens
164K
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
Not supported
Fim Completion
Not supported
Not supported
Chat Prefix Completion
Supported
Not supported
DeepSeek-V3.2-Exp in Comparison
See how DeepSeek-V3.2-Exp compares with other popular models across key dimensions.
