Model Comparison
gpt-oss-120b
vs
MiniMax-M2.5
Feb 15, 2026
Pricing
Input
$
0.05
/ M Tokens
$
0.3
/ M Tokens
Output
$
0.45
/ M Tokens
$
1.2
/ M Tokens
Metadata
Create on
Aug 4, 2025
Feb 12, 2026
License
APACHE-2.0
MODIFIED-MIT
Provider
OpenAI
MiniMaxAI
Specification
State
Available
Available
Architecture
Mixture of Experts
MoE
Calibrated
Yes
No
Mixture of Experts
Yes
Yes
Total Parameters
120B
229B
Activated Parameters
5.1B
Reasoning
No
No
Precision
FP8
FP8
Context length
131K
197K
Max Tokens
8K
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
Supported
Structured Outputs
Not supported
Not supported
Tools
Not supported
Supported
Fim Completion
Not supported
Not supported
Chat Prefix Completion
Not supported
Supported
gpt-oss-120b in Comparison
See how gpt-oss-120b compares with other popular models across key dimensions.
