Model Library
GPUs
GPU Instance
High-performance GPU Instances
Bare Metal
AI-Specific Bare Metal GPUs
Serverless
Serverless Inference
Storage
AI-Optimized Storage
Solutions
Pricing
Blog
Docs
Contact
Contact
Model Library
GPUs
GPU Instance
High-performance GPU instances
Bare Metal
Dedicated GPU servers
Serverless
Serverless computing platform
Storage
Cloud storage solutions
Solutions
Pricing
Blog
Docs
Chat
deepseek-ai/DeepSeek-V3.1
API View
$0.32/M
input
$1.15/M
output
Deep Thinking
Model
Settings
Output Length
1
65535
Temperature
0
2
Top-P
0
1
Top-K
1
100
Repetition Penalty
1
2
System Prompt