DeepSeek V3 0324
by Hugging Face · family deepseek · listed Mar 2025TW
DeepSeek chat model for instruction following, coding, and analysis
Current rates USD per 1M tokens
Input$0.27
Output$1.12
Cache read—
Cache write—
Against the market
On the record
- Model id
deepseek-ai/DeepSeek-V3-0324- Context window
- 164K tokens
- Max output
- 164K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2025-03-24
- Last updated
- 2025-03-24
- Provider docs
- huggingface.co/docs/inference-providers
Back of the envelope
≈
Also listed at
- NanoGPT$0.20 in · $0.77 out
- submodel$0.20 in · $0.80 out
- Deep Infra$0.24 in · $0.90 out
- Alibaba (China)$0.25 in · $1.00 out
- Meganova$0.25 in · $0.88 out
- NovitaAI$0.27 in · $1.12 out
- Jiekou.AI$0.28 in · $1.14 out
- Crusoe$0.50 in · $1.50 out
- Qiniu— in · — out