All Models
DeepSeek V3 (0324)
DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well on a variety of tasks.
Benchmarks
Available Providers (14)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 OpenRouter | deepseek/deepseek-chat-v3-0324 | $0.00/MTok | $0.00/MTok | 16.4K | 8.2K | |
 GitHub Models | deepseek/deepseek-v3-0324 | $0.00/MTok | $0.00/MTok | 128K | 8.2K | |
 submodel | deepseek-ai/DeepSeek-V3-0324 | $0.20/MTok | $0.80/MTok | 75K | 163.8K | |
 Meganova | deepseek-ai/DeepSeek-V3-0324 | $0.25/MTok | $0.88/MTok | 163.8K | 163.8K | |
 NovitaAI | deepseek/deepseek-v3-0324 | $0.27/MTok | $1.12/MTok | 163.8K | 163.8K | |
 Jiekou.AI | deepseek/deepseek-v3-0324 | $0.28/MTok | $1.14/MTok | 163.8K | 163.8K | |
 Nebius Token Factory | deepseek-ai/DeepSeek-V3-0324 | $0.50/MTok | $1.50/MTok | 128K | 8.2K | |
 Cortecs | deepseek-v3-0324 | $0.55/MTok | $1.65/MTok | 128K | 128K | |
 Vercel AI Gateway | deepseek/deepseek-v3 | $0.77/MTok | $0.77/MTok | 163.8K | 16.4K | |
 Baseten | deepseek-ai/DeepSeek-V3-0324 | $0.77/MTok | $0.77/MTok | 164K | 131K | |
 Azure Cognitive Services | deepseek-v3-0324 | $1.14/MTok | $4.56/MTok | 131.1K | 131.1K | |
 Azure | deepseek-v3-0324 | $1.14/MTok | $4.56/MTok | 131.1K | 131.1K | |
 Synthetic | hf:deepseek-ai/DeepSeek-V3-0324 | $1.20/MTok | $1.20/MTok | 128K | 128K | |
 Qiniu | deepseek-v3-0324 | —/MTok | —/MTok | 128K | 16K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output