DeepSeek: R1
DeepSeek reasoning model for multi-step analysis, math, coding, and tools
Sources
Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| LiteLLMcheapesthyperbolic/deepseek-ai/DeepSeek-R1 | N/A | $0.4 | $0.4 | $0.04 | N/A |
| models.devdeepseek-ai/DeepSeek-R1 | SiliconFlow | $0.5 | $2.18 | $0 | 164K |
| models.devpublic/deepseek-r1 | D.Run (China) | $0.55 | $2.20 | $0 | 131K |
| LiteLLMdeepseek-r1 | N/A | $0.55 | $2.19 | $0.14 | N/A |
| LiteLLMdeepseek/deepseek-r1 | N/A | $0.55 | $2.19 | $0.14 | N/A |
| LiteLLMvercel_ai_gateway/deepseek/deepseek-r1 | N/A | $0.55 | $2.19 | $0.055 | N/A |
| LiteLLMstreamlake/deepseek-r1 | N/A | $0.571 | $2.29 | $0.229 | N/A |
| models.devdeepseek-r1 | Alibaba / Qwen | $0.574 | $2.29 | $0 | 131K |
| models.devdeepseek-r1 | Qiniu | $0.5797 | $2.32 | $0 | 128K |
| models.devPro/deepseek-ai/DeepSeek-R1 | SiliconFlow (China) | $0.5978 | $2.39 | $0.0598 | 164K |
| models.devdeepinfra/deepseek-ai/DeepSeek-R1 | Eden AI | $0.7 | $2.40 | $0 | 164K |
| models.devdeepseek-ai/DeepSeek-R1 | Hugging Face | $0.7 | $2.50 | $0 | 64K |
| LiteLLMdeepseek-ai/DeepSeek-R1 | N/A | $0.7 | $2.40 | $0.07 | N/A |
| LiteLLMDeepSeek-R1 | N/A | $0.7 | $2.40 | $0.07 | N/A |
| LiteLLMdeepinfra/deepseek-ai/DeepSeek-R1 | N/A | $0.7 | $2.40 | $0.07 | N/A |
| LiteLLMkyma/deepseek-r1 | N/A | $0.7425 | $2.96 | $0.0742 | N/A |
| LiteLLMnebius/deepseek-ai/DeepSeek-R1 | N/A | $0.8 | $2.40 | $0.08 | N/A |
| models.devdeepseek/deepseek-r1 | Merge Gateway | $1.35 | $5.40 | $0 | 164K |
| models.devdeepseek/deepseek-r1 | Vercel AI Gateway | $1.35 | $5.40 | $0 | 128K |
| LiteLLMazure_ai/deepseek-r1 | N/A | $1.35 | $5.40 | $0.135 | N/A |
| LiteLLMsnowflake/deepseek-r1 | N/A | $1.35 | $5.40 | $0.135 | N/A |
| models.devdeepseek-ai/DeepSeek-R1 | Abacus | $3 | $7 | $0 | 128K |
| models.devdeepseek-ai/DeepSeek-R1 | Together AI | $3 | $7 | $0 | 164K |
| LiteLLMaccounts/fireworks/models/deepseek-r1 | N/A | $3 | $8 | $0.3 | N/A |
| LiteLLMfireworks_ai/accounts/fireworks/models/deepseek-r1 | N/A | $3 | $8 | $0.3 | N/A |
| LiteLLMdeepseek-ai/deepseek-r1 | N/A | $3.75 | $10 | $0.375 | N/A |
| LiteLLMreplicate/deepseek-ai/deepseek-r1 | N/A | $3.75 | $10 | $0.375 | N/A |
| LiteLLMnovita/deepseek/deepseek-r1 | N/A | $4 | $4 | $0.4 | N/A |
| LiteLLMsambanova/DeepSeek-R1 | N/A | $5 | $7 | $0.5 | N/A |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Open weights
- In: text
- Out: text
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.
- AA intelligence11.4i
- AA coding24.6i
- AA agentic1.1i
Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.
See what this model costs you
The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.