deepseek-r1
The latest revision of DeepSeek's first-generation reasoning model
| Provider | Source | Input Price ($/1M) | Output Price ($/1M) | Description | Free |
|---|---|---|---|---|---|
| vercel | vercel | Input: $0.50 | Output: $2.15 | The latest revision of DeepSeek's first-generation reasoning model | |
| together | together | Input: $3.00 | Output: $7.00 | - | |
| poe | poe | Input: $18,000.00 | Output: - | Top open-source reasoning LLM rivaling OpenAI's o1 model; delivers top-tier performance across math, code, and reasoning tasks at a fraction of the cost. All data you provide this bot will not be used in training, and is sent only to Together AI, a US-based company. Supports 164k tokens of input context and 33k tokens of output context. Uses the latest May 28th snapshot (DeepSeek-R1-0528). | |
| nvidia | models-dev | Input: $0.00 | Output: $0.00 | Provider: Nvidia, Context: 128000, Output Limit: 4096 | |
| alibabacn | models-dev | Input: $0.57 | Output: $2.29 | Provider: Alibaba (China), Context: 131072, Output Limit: 16384 | |
| siliconflowcn | models-dev | Input: $0.50 | Output: $2.18 | Provider: SiliconFlow (China), Context: 164000, Output Limit: 164000 | |
| githubmodels | models-dev | Input: $0.00 | Output: $0.00 | Provider: GitHub Models, Context: 65536, Output Limit: 8192 | |
| togetherai | models-dev | Input: $3.00 | Output: $7.00 | Provider: Together AI, Context: 163839, Output Limit: 12288 | |
| azure | models-dev | Input: $1.35 | Output: $5.40 | Provider: Azure, Context: 163840, Output Limit: 163840 | |
| siliconflow | models-dev | Input: $0.50 | Output: $2.18 | Provider: SiliconFlow, Context: 164000, Output Limit: 164000 | |
| iflowcn | models-dev | Input: $0.00 | Output: $0.00 | Provider: iFlow, Context: 128000, Output Limit: 32000 | |
| synthetic | models-dev | Input: $0.55 | Output: $2.19 | Provider: Synthetic, Context: 128000, Output Limit: 128000 | |
| nanogpt | models-dev | Input: $1.00 | Output: $2.00 | Provider: NanoGPT, Context: 128000, Output Limit: 8192 | |
| azurecognitiveservices | models-dev | Input: $1.35 | Output: $5.40 | Provider: Azure Cognitive Services, Context: 163840, Output Limit: 163840 | |
| azureai | litellm | Input: $1.35 | Output: $5.40 | Source: azure_ai, Context: 128000 | |
| deepinfra | litellm | Input: $0.70 | Output: $2.40 | Source: deepinfra, Context: 163840 | |
| deepseek | litellm | Input: $0.55 | Output: $2.19 | Source: deepseek, Context: 65536 | |
| fireworksai | litellm | Input: $3.00 | Output: $8.00 | Source: fireworks_ai, Context: 128000 | |
| hyperbolic | litellm | Input: $0.40 | Output: $0.40 | Source: hyperbolic, Context: 32768 | |
| sambanova | litellm | Input: $5.00 | Output: $7.00 | Source: sambanova, Context: 32768 | |
| snowflake | litellm | Input: $0.00 | Output: $0.00 | Source: snowflake, Context: 32768 | |
| openrouter | openrouter | Input: $0.70 | Output: $2.40 | 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. Fully open-source model & [technical report](https://api-docs.deepseek.com/news/news250120). MIT licensed: Distill & commercialize freely! Context: 163840 |