DeepSeek V4 Pro 0813
by Hugging Face · family deepseek-thinking · listed Aug 2026RTW
Flagship DeepSeek model for coding, reasoning, and agentic work
Current rates USD per 1M tokens
Input$1.32
Output$3.96
Cache read—
Cache write—
Against the market
On the record
- Model id
deepseek-ai/DeepSeek-V4-Pro-0813- Context window
- 1M tokens
- Max output
- 384K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2026-08-12
- Last updated
- 2026-08-12
- Provider docs
- huggingface.co/docs/inference-providers
Back of the envelope
≈
Also listed at
- Alibaba Token Planfree in · free out
- Alibaba Token Plan (China)free in · free out
- Merge Gateway$0.435 in · $0.87 out
- NanoGPT$1.10 in · $2.50 out
- Deep Infra$1.30 in · $2.60 out
- Eden AI$1.30 in · $2.60 out
- Cloudflare Workers AI$1.32 in · $3.96 out
- OpenRouter$1.32 in · $3.96 out
- DigitalOcean$1.32 in · $3.96 out
- Arcee$1.32 in · $3.96 out
- Together AI$1.32 in · $3.96 out
- Ofox$1.32 in · $3.96 out
- Charm Hyper$1.32 in · $3.96 out
- Baseten$1.32 in · $3.96 out
- EmpirioLabs AI$1.32 in · $3.96 out