Model Comparison
DeepSeek-V3
vs
Step-3.5-Flash
Feb 15, 2026
Pricing
Input
$
0.25
/ M Tokens
$
0.1
/ M Tokens
Output
$
1.0
/ M Tokens
$
0.3
/ M Tokens
Metadata
Create on
Dec 25, 2024
Feb 1, 2026
License
MODEL AGREEMENT
APACHE 2.0
Provider
DeepSeek
StepFun
Specification
State
Available
Available
Architecture
MoE
Sparse Mixture-of-Experts (MoE) transformer architecture
Calibrated
No
No
Mixture of Experts
Yes
Yes
Total Parameters
671B
196B
Activated Parameters
37B
11B
Reasoning
No
No
Precision
FP8
FP8
Context length
164K
262K
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
Not supported
Structured Outputs
Not supported
Not supported
Tools
Supported
Supported
Fim Completion
Supported
Not supported
Chat Prefix Completion
Supported
Supported
DeepSeek-V3 in Comparison
See how DeepSeek-V3 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
GLM-4.6V
VS
DeepSeek-V3.2
VS
DeepSeek-V3.1-Nex-N1
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
DeepSeek-V3.1
