DeepSeek V4 Pro 0813
Provider：DeepSeek
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
Key specs
- Context：1M
- Max output：384K
- Tokenizer：DeepSeek
- Released：2026-08-12
Token pricing
- Input price：$0.660 / 1M tokens
- Output price：$1.98 / 1M tokens
- Cache read：$0.022 / 1M tokens
- Blended price：$0.990 / 1M tokens
Modalities
Text
Use Cases
- Deep Reasoning & Analysis：Process long legal docs, academic papers, financial reports; multi-hop reasoning and evidence-chain tracing across huge contexts.（≈ $0.016/call）
When to pick this model
Signals derived from public pricing and spec fields — not a benchmark. Validate with official docs and your own eval.
- Long context (>=1M tokens): well-suited for long-doc QA, code-base analysis, multi-turn agents.
- Long max output (>=30K tokens): strong fit for deep report / essay / document-drafting workflows.
FAQ
- What is the token pricing of DeepSeek V4 Pro 0813? Input price $0.660 / 1M tokens, output price $1.98 / 1M tokens, blended about $0.990 / 1M tokens. Refer to DeepSeek’s official page for the exact rate.
- What context window does DeepSeek V4 Pro 0813 support? Context window is 1M, max output about 384K, suitable for long documents, multi-turn chat and complex reasoning.
- What scenarios is DeepSeek V4 Pro 0813 best for? Based on its capability and pricing, DeepSeek V4 Pro 0813 fits best: Deep Reasoning & Analysis. See the Use Cases section for details and cost estimates.
- What input/output modalities does DeepSeek V4 Pro 0813 support? Supports Text modality.
- Is DeepSeek V4 Pro 0813 a free model? DeepSeek V4 Pro 0813 is billed per token, not a free model.
- Which provider offers DeepSeek V4 Pro 0813? DeepSeek V4 Pro 0813 is offered by DeepSeek.
More models from DeepSeek
Full info：DeepSeek V4 Pro 0813