DeepSeek R1 0528
by Alibaba (China) · family deepseek-thinking · listed May 2025RT
DeepSeek reasoning model for multi-step analysis, math, coding, and tools
Current rates USD per 1M tokens
Input$0.574
Output$2.29
Cache read—
Cache write—
Against the market
On the record
- Model id
deepseek-r1-0528- Context window
- 131K tokens
- Max output
- 16K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2025-05-28
- Last updated
- 2025-05-28
- Provider docs
- www.alibabacloud.com/help/en/model-studio/models
Back of the envelope
≈
Also listed at
- GitHub Modelsfree in · free out
- NanoGPT$0.40 in · $1.70 out
- Kilo Gateway$0.45 in · $2.15 out
- submodel$0.50 in · $2.15 out
- Deep Infra$0.50 in · $2.15 out
- Meganova$0.50 in · $2.15 out
- OpenRouter$0.50 in · $2.15 out
- Cortecs$0.585 in · $2.31 out
- NovitaAI$0.70 in · $2.50 out
- Jiekou.AI$0.70 in · $2.50 out
- Azure$1.35 in · $5.40 out
- Azure Cognitive Services$1.35 in · $5.40 out
- IO.NET$2.00 in · $8.75 out
- Hugging Face$3.00 in · $5.00 out
- Qiniu— in · — out