DeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813 is a large language model made by DeepSeek, added to the catalog on 12 Aug 2026. It has a context window of 1,048,576 tokens and costs $1.32 per 1M input tokens and $3.96 per 1M output tokens. It accepts text and produces text. Typical uses: reviewing and summarizing long documents, drafting and revising text and reasoning over written material.
Price checked · source: OpenRouter
What DeepSeek V4 Pro 0813 is
DeepSeek V4 Pro 0813 is DeepSeek’s GA release of a large-scale mixture-of-experts model. It accepts text and produces text. The context window is 1,048,576 tokens, and the maximum output is 943,718 tokens. These limits describe the amount of text the model can take in as context and generate as output, respectively, making its stated capacity relevant to work involving extensive written material.
It supports reasoning, tools, structured outputs, and response formats. Those features suit text-based tasks that call for reasoning over supplied material, interaction with tools, or answers organized to a requested structure or format. The context window may be useful when a task brings together long documents, several source texts, or lengthy instructions, while the output limit allows for long text responses within the stated maximum. Suitable task types include reviewing and summarizing long documents, drafting or revising text, working through written questions, and producing formatted or structured responses. Its tool support can fit workflows in which text requests include tool use; the facts do not specify which tools are available. The listed modalities are text for both input and output; the catalog facts do not describe image or audio handling. The model is identified as DeepSeek V4 Pro’s GA release, specifically the 0813 version.
Key features
- Accepts text and produces text
- Has a 1,048,576-token context window
- Supports reasoning and tools
- Supports structured outputs and response formats
- Maximum output is 943,718 tokens
Typical uses
- Reviewing and summarizing long documents
- Drafting and revising text
- Reasoning over written material
- Producing structured or formatted responses
DeepSeek V4 Pro 0813 pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $1.32 |
| Output, per 1M tokens | $3.96 |
| Cached input read, per 1M tokens | $0.044 |
No price change since it was added on 12 Aug 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0018 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.036 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.048 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.204 |
DeepSeek V4 Pro 0813 specifications
| Model id | deepseek/deepseek-v4-pro-0813 |
|---|---|
| Version | deepseek-v4-pro-20260813 |
| Context window | 1,048,576 tokensAbout 786,432 English words |
| Max output | 943,718 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 12 Aug 2026 |
| Input types | text |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for DeepSeek V4 Pro 0813 yet.
Compare DeepSeek V4 Pro 0813
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.