Model Comparison
DeepSeek-V3.1-Nex-N1
vs
step3
Feb 28, 2026
Pricing
Input
$
0.27
/ M Tokens
$
0.57
/ M Tokens
Output
$
1.0
/ M Tokens
$
1.42
/ M Tokens
Metadata
Create on
Nov 18, 2025
Jul 28, 2025
License
APACHE-2.0
APACHE LICENSE (VERSION 2.0)
Provider
Nex AGI
StepFun
Specification
State
Available
Deprecated
Architecture
Mixture of Experts
Mixture-of-Experts (MoE) architecture with Multi-Matrix Factorization Attention (MFA) and Attention-FFN Disaggregation (AFD)
Calibrated
No
No
Mixture of Experts
Yes
Yes
Total Parameters
670B
321B
Activated Parameters
670B
38B
Reasoning
No
No
Precision
FP8
FP8
Context length
131K
66K
Max Tokens
164K
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
Supported
Supported
Structured Outputs
Not supported
Not supported
Tools
Supported
Supported
Fim Completion
Not supported
Not supported
Chat Prefix Completion
Not supported
Not supported
DeepSeek-V3.1-Nex-N1 in Comparison
See how DeepSeek-V3.1-Nex-N1 compares with other popular models across key dimensions.
VS
MiniMax-M2.5
VS
GLM-5
VS
Step-3.5-Flash
VS
GLM-4.7
VS
MiniMax-M2.1
VS
GLM-4.6V
VS
DeepSeek-V3.2
VS
Kimi-K2-Thinking
VS
MiniMax-M2
VS
DeepSeek-V3.2-Exp
VS
GLM-4.6
VS
DeepSeek-V3.1-Terminus
VS
Qwen3-VL-235B-A22B-Instruct
VS
Qwen3-VL-235B-A22B-Thinking
VS
Ring-flash-2.0
VS
Ling-flash-2.0
VS
Kimi-K2-Instruct-0905
VS
GLM-4.5V
VS
gpt-oss-120b
VS
step3
