DeepSeek
DeepSeek-R1
DeepSeek reasoning model for multi-step analysis, math, coding, and tools
Model facts
- Context window
- 128K tokens
- Maximum output
- 33K tokens
- Cheapest paid input
- $0.4 per 1M tokens
- Cheapest paid output
- $1.7 per 1M tokens
- Open weights
- yes
- Providers
- 19
Capabilities and modalities
reasoning, tool calling, structured output, temperature control, open weights, text.
Local hardware estimate
At 4K context: Q4_K_M 419.9 GiB, Q8_0 738.7 GiB, F16 1336.4 GiB working memory.
- Parameters
- 684.5 billion
- Architecture
- deepseekv3
- Model license
- mit
Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.
Artificial Analysis benchmarks
Compare this model on the full LLM benchmark leaderboard.
| Configuration | AAI | Coding | Math | Output tokens/s |
|---|---|---|---|---|
| Jan '25 | 18.6 | 24.6 | 68.0 | not measured |
Observed price history
- 2026-08-24: $0.4 input / $1.7 output per 1M tokens
API providers
- iFlow — model id deepseek-r1; free input / free output per 1M tokens; provider documentation
- NanoGPT — model id deepseek-r1; $0.4 input / $1.7 output per 1M tokens; provider documentation
- D.Run (China) — model id public/deepseek-r1; $0.55 input / $2.2 output per 1M tokens; provider documentation
- Alibaba (China) — model id deepseek-r1; $0.574 input / $2.29 output per 1M tokens; provider documentation
- Eden AI — model id deepinfra/deepseek-ai/DeepSeek-R1; $0.7 input / $2.4 output per 1M tokens; provider documentation
- Hugging Face — model id deepseek-ai/DeepSeek-R1; $0.7 input / $2.5 output per 1M tokens; provider documentation
- Kilo Gateway — model id deepseek/deepseek-r1; $0.7 input / $2.5 output per 1M tokens; provider documentation
- OpenRouter — model id deepseek/deepseek-r1; $0.7 input / $2.5 output per 1M tokens; provider documentation
- Amazon Bedrock — model id deepseek.r1-v1:0; $1.35 input / $5.4 output per 1M tokens; provider documentation
- Amazon Bedrock (US) — model id us.deepseek.r1-v1:0; $1.35 input / $5.4 output per 1M tokens; provider documentation
- Azure — model id deepseek-r1; $1.35 input / $5.4 output per 1M tokens; provider documentation
- Azure Cognitive Services — model id deepseek-r1; $1.35 input / $5.4 output per 1M tokens; provider documentation
- Merge Gateway — model id deepseek/deepseek-r1; $1.35 input / $5.4 output per 1M tokens; provider documentation
- Vercel AI Gateway — model id deepseek/deepseek-r1; $1.35 input / $5.4 output per 1M tokens; provider documentation
- Abacus — model id deepseek-ai/DeepSeek-R1; $3 input / $7 output per 1M tokens; provider documentation
- Together AI — model id deepseek-ai/DeepSeek-R1; $3 input / $7 output per 1M tokens; provider documentation
- IO.NET — model id deepseek-ai/DeepSeek-R1-0528; $2 input / $8.75 output per 1M tokens; provider documentation
- Qiniu — model id deepseek-r1; not published input / not published output per 1M tokens; provider documentation
- Snowflake Cortex — model id deepseek-r1; not published input / not published output per 1M tokens; provider documentation