DeepSeek-V3
DeepSeek's large general-purpose mixture-of-experts model.
Overview
DeepSeek-V3 is DeepSeek's large general-purpose mixture-of-experts model, released in December 2024. It activates 37B of its 671B parameters per token, giving strong performance across chat, coding and analysis at a lower running cost than a dense model of similar quality. Self-hosting it requires a multi-GPU server.
| Weights | Open |
|---|---|
| Parameters | 671B total, 37B active (mixture of experts) |
| Context window | 128K tokens |
| Licence | DeepSeek Model License |
| Commercial use | Yes |
LLM hosts that offer DeepSeek-V3
All hosts →| LLM host | Hosting plan | Hosting type | Pricing |
|---|---|---|---|
| Amazon AWS | Amazon EC2 | GPU cloud | From US$0.526Per GPU-hour, Reserved or committed capacity |
| Google Cloud | Google Kubernetes Engine (GKE) | GPU cloud | From US$0.35Per GPU-hour, Reserved or committed capacity |
| Google Cloud | Compute Engine | GPU cloud | From US$0.35Per GPU-hour, Reserved or committed capacity |
| Microsoft Azure | Azure Machine Learning | Dedicated endpoint | From US$0.526Per GPU-hour, Reserved or committed capacity |
| Microsoft Azure | Azure Kubernetes Service (AKS) | GPU cloud | From US$0.526Per GPU-hour, Reserved or committed capacity |
| Microsoft Azure | Azure GPU Virtual Machines | GPU cloud | From US$0.526Per GPU-hour, Reserved or committed capacity |