All Models
Deepseek R1 0528
May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass. Fully open-source model.
Available Providers (16)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 Nvidia | deepseek-ai/deepseek-r1-0528 | $0.00/MTok | $0.00/MTok | 128K | 4.1K | |
 GitHub Models | deepseek/deepseek-r1-0528 | $0.00/MTok | $0.00/MTok | 65.5K | 8.2K | |
 NanoGPT | deepseek-ai/DeepSeek-R1-0528 | $0.40/MTok | $1.70/MTok | 128K | 163.8K | |
 Kilo Gateway | deepseek/deepseek-r1-0528 | $0.45/MTok | $2.15/MTok | 163.8K | 65.5K | |
 Deep Infra | deepseek-ai/DeepSeek-R1-0528 | $0.50/MTok | $2.15/MTok | 163.8K | 64K | |
 submodel | deepseek-ai/DeepSeek-R1-0528 | $0.50/MTok | $2.15/MTok | 75K | 163.8K | |
 Meganova | deepseek-ai/DeepSeek-R1-0528 | $0.50/MTok | $2.15/MTok | 163.8K | 64K | |
 Alibaba (China) | deepseek-r1-0528 | $0.57/MTok | $2.29/MTok | 131.1K | 16.4K | |
 NovitaAI | deepseek/deepseek-r1-0528 | $0.70/MTok | $2.50/MTok | 163.8K | 32.8K | |
 Jiekou.AI | deepseek/deepseek-r1-0528 | $0.70/MTok | $2.50/MTok | 163.8K | 32.8K | |
 Nebius Token Factory | deepseek-ai/DeepSeek-R1-0528 | $0.80/MTok | $2.40/MTok | 128K | 32.8K | |
 Azure Cognitive Services | deepseek-r1-0528 | $1.35/MTok | $5.40/MTok | 163.8K | 163.8K | |
 Azure | deepseek-r1-0528 | $1.35/MTok | $5.40/MTok | 163.8K | 163.8K | |
 Synthetic | hf:deepseek-ai/DeepSeek-R1-0528 | $3.00/MTok | $8.00/MTok | 128K | 128K | |
 Hugging Face | deepseek-ai/DeepSeek-R1-0528 | $3.00/MTok | $5.00/MTok | 163.8K | 163.8K | |
 Qiniu | deepseek-r1-0528 | —/MTok | —/MTok | 128K | 32K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output