Model Comparison
MiniMax-M2.5
vs
Qwen3-VL-235B-A22B-Thinking
Feb 15, 2026
Pricing
Input
$
0.3
/ M Tokens
$
0.45
/ M Tokens
Output
$
1.2
/ M Tokens
$
3.5
/ M Tokens
Metadata
Create on
Feb 12, 2026
Sep 22, 2025
License
MODIFIED-MIT
APACHE-2.0
Provider
MiniMaxAI
Qwen
Specification
State
Available
Available
Architecture
Mixture-of-Experts (MoE)
Mixture-of-Experts
Calibrated
No
No
Mixture of Experts
Yes
Yes
Total Parameters
229B
235B
Activated Parameters
229B
22B
Reasoning
No
No
Precision
FP8
FP8
Context length
197K
262K
Max Tokens
131K
262K
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
Supported
Structured Outputs
Not supported
Not supported
Tools
Supported
Supported
Fim Completion
Not supported
Supported
Chat Prefix Completion
Supported
Supported
MiniMax-M2.5 in Comparison
See how MiniMax-M2.5 compares with other popular models across key dimensions.
