All Models
DeepSeek-R1
DeepSeek R1 is here: 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....
Benchmarks
Available Providers (17)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 GitHub Models | deepseek/deepseek-r1 | $0/MTok | $0/MTok | 65.5K | 8.2K | |
 iFlow | deepseek-r1 | $0/MTok | $0/MTok | 128K | 32K | |
 NanoGPT | deepseek-r1 | $0.40/MTok | $1.70/MTok | 128K | 8.2K | |
 D.Run (China) | public/deepseek-r1 | $0.55/MTok | $2.20/MTok | 131.1K | 32K | |
 Synthetic | hf:deepseek-ai/DeepSeek-R1 | $0.55/MTok | $2.19/MTok | 128K | 128K | |
 Alibaba (China) | deepseek-r1 | $0.57/MTok | $2.29/MTok | 131.1K | 16.4K | |
 Hugging Face | deepseek-ai/DeepSeek-R1 | $0.70/MTok | $2.50/MTok | 64K | 32.8K | |
 OpenRouter | deepseek/deepseek-r1 | $0.70/MTok | $2.50/MTok | 64K | 16K | |
 Vercel AI Gateway | deepseek/deepseek-r1 | $1.35/MTok | $5.40/MTok | 128K | 32.8K | |
 Azure | deepseek-r1 | $1.35/MTok | $5.40/MTok | 163.8K | 163.8K | |
 Amazon Bedrock | deepseek.r1-v1:0 | $1.35/MTok | $5.40/MTok | 128K | 32.8K | |
 Azure Cognitive Services | deepseek-r1 | $1.35/MTok | $5.40/MTok | 163.8K | 163.8K | |
 IO.NET | deepseek-ai/DeepSeek-R1-0528 | $2/MTok | $8.75/MTok | 128K | 4.1K | |
 Abacus | deepseek-ai/DeepSeek-R1 | $3/MTok | $7/MTok | 128K | 8.2K | |
 Together AI | deepseek-ai/DeepSeek-R1 | $3/MTok | $7/MTok | 163.8K | 163.8K | |
 Qiniu | deepseek-r1 | —/MTok | —/MTok | 128K | 32K | |
 Snowflake Cortex | deepseek-r1 | —/MTok | —/MTok | 128K | 32.8K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output