Model Comparison
MiniMax-M1-80k
vs
step3
Feb 28, 2026
Pricing
Input
$
0.55
/ M Tokens
$
0.57
/ M Tokens
Output
$
2.2
/ M Tokens
$
1.42
/ M Tokens
Metadata
Create on
Jun 13, 2025
Jul 28, 2025
License
APACHE 2.0
APACHE LICENSE (VERSION 2.0)
Provider
MiniMaxAI
StepFun
Specification
State
Deprecated
Deprecated
Architecture
hybrid-attention Mixture-of-Experts (MoE)
Mixture-of-Experts (MoE) architecture with Multi-Matrix Factorization Attention (MFA) and Attention-FFN Disaggregation (AFD)
Calibrated
Yes
No
Mixture of Experts
Yes
Yes
Total Parameters
456B
321B
Activated Parameters
45.9B
38B
Reasoning
No
No
Precision
FP8
FP8
Context length
131K
66K
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
Supported
Structured Outputs
Not supported
Not supported
Tools
Not supported
Supported
Fim Completion
Not supported
Not supported
Chat Prefix Completion
Not supported
Not supported
MiniMax-M1-80k in Comparison
See how MiniMax-M1-80k compares with other popular models across key dimensions.
