DeepSeek V4 Pro 0813
by Venice AI · family deepseek-thinking · listed Aug 2026RT
Flagship DeepSeek model for coding, reasoning, and agentic work
Current rates USD per 1M tokens
Input$1.65
Output$4.95
Cache read$0.165
Cache write—
Against the market
On the record
- Model id
deepseek-v4-pro-0813- Context window
- 1M tokens
- Max output
- 33K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2026-08-14
- Last updated
- 2026-08-14
- Provider docs
- docs.venice.ai
Back of the envelope
≈
Also listed at
- Alibaba Token Planfree in · free out
- Alibaba Token Plan (China)free in · free out
- RunInfra$0.60 in · $1.90 out
- Merge Gateway$0.66 in · $1.98 out
- Eden AI$0.726 in · $2.18 out
- NanoGPT$1.10 in · $2.50 out
- OpenRouter$1.19 in · $3.56 out
- Requesty$1.19 in · $3.56 out
- Deep Infra$1.30 in · $2.60 out
- Cloudflare Workers AI$1.32 in · $3.96 out
- Hugging Face$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