DeepSeek V4 Pro
by SenseNova (China) · family deepseek-thinking · listed Aug 2026RTW
DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes
Current rates USD per 1M tokens
Inputfree
Outputfree
Cache readfree
Cache write—
Against the market
On the record
- Model id
deepseek-v4-pro- Context window
- 1.0M tokens
- Max output
- 66K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2026-08-13
- Last updated
- 2026-08-22
- Provider docs
- platform.sensenova.cn/docs
Back of the envelope
≈
Also listed at
- SCNet Token Planfree in · free out
- Alibaba Token Planfree in · free out
- Volcengine Ark Coding Planfree in · free out
- Alibaba Token Plan (China)free in · free out
- routing.run$0.348 in · $0.696 out
- EBCloud$0.429 in · $0.857 out
- Modelis$0.435 in · $0.87 out
- Pioneer$0.435 in · $0.87 out
- LLM Gateway$0.435 in · $0.87 out
- DevPass (LLM Gateway)$0.435 in · $0.87 out
- Hugging Face$0.435 in · $0.87 out
- TokenGo$0.435 in · $0.87 out
- Kenari$0.571 in · $1.14 out
- CommandCode$0.66 in · $1.98 out
- ClinePass$0.66 in · $1.98 out