DeepSeek-V3.1
by Azure Cognitive Services · family deepseek · listed Aug 2025RTW
DeepSeek chat model for instruction following, coding, and analysis
Current rates USD per 1M tokens
Input$0.56
Output$1.68
Cache read—
Cache write—
Against the market
On the record
- Model id
deepseek-v3.1- Context window
- 131K tokens
- Max output
- 131K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- Jul 2024
- Released
- 2025-08-21
- Last updated
- 2025-08-21
Back of the envelope
≈
Also listed at
- submodel$0.20 in · $0.80 out
- NanoGPT$0.20 in · $0.70 out
- NovitaAI$0.27 in · $1.00 out
- SiliconFlow$0.27 in · $1.00 out
- Meganova$0.27 in · $1.00 out
- Jiekou.AI$0.27 in · $1.00 out
- Baseten$0.50 in · $1.50 out
- Abacus$0.55 in · $1.66 out
- Weights & Biases$0.55 in · $1.65 out
- LLM Gateway$0.56 in · $1.68 out
- Azure$0.56 in · $1.68 out
- Vercel AI Gateway$0.60 in · $1.70 out
- Qiniu— in · — out