# DeepSeek-V4-Pro (0813)

> A DeepSeek text model with a 1,048,576-token context window and a 393,216-token maximum output, supporting reasoning and tool calling.

## Key facts

- Model author: DeepSeek
- Input: $1.32 per 1M tokens
- Output: $3.96 per 1M tokens
- Cached input: $0.042 per 1M tokens
- Context window: 1,048,576 tokens
- Maximum output: 393,216 tokens
- Input modalities: text
- Output modalities: text
- Capabilities: reasoning, structured_output, tools
- Released: 2026-08-12
- Model IDs: `baidu/deepseek-v4-pro-0813`
- Model page: https://www.realrelay.ai/model/deepseek/deepseek-v4-pro-0813

## Overview

DeepSeek-V4-Pro (0813) is a DeepSeek text model. It accepts text input and returns text output, and it supports reasoning, tool calling and structured output.

The context window is 1,048,576 tokens and the maximum output is 393,216 tokens. The model was released on August 12, 2026, and requests are served through RealRelay's OpenAI-compatible endpoint under the model ID baidu/deepseek-v4-pro-0813.

## Capabilities

DeepSeek-V4-Pro (0813) supports reasoning, tool calling and structured output.

Input and output modalities are text only, so the model works with text prompts and text responses.

## Pricing

Usage is metered by tokens: $1.32 per 1M input tokens and $3.96 per 1M output tokens, with cached input reads at $0.042 per 1M tokens.

## Use Cases

DeepSeek-V4-Pro (0813) is suited for reasoning and agent workflows.

Tool calling and structured output are available for programmatic use, and the model offers a 1,048,576-token context window with a 393,216-token maximum output.

## Call it

OpenAI-compatible chat completions:

```bash
curl https://www.realrelay.ai/v1/chat/completions \
  -H "Authorization: Bearer $REALRELAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "baidu/deepseek-v4-pro-0813", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is DeepSeek-V4-Pro (0813)?

It is a DeepSeek text model that accepts text input and returns text output, and it supports reasoning, tool calling and structured output.

### What is the price of DeepSeek-V4-Pro (0813)?

$1.32 per 1M input tokens and $3.96 per 1M output tokens, with cached input reads at $0.042 per 1M tokens. Usage is metered by tokens.

### What is the context window of DeepSeek-V4-Pro (0813)?

The context window is 1,048,576 tokens, and the maximum output is 393,216 tokens.

### What input and output modalities does DeepSeek-V4-Pro (0813) support?

Input and output are text only: the model takes text prompts and returns text responses.

### Which capabilities does DeepSeek-V4-Pro (0813) support?

It supports reasoning, tool calling and structured output.

### When was DeepSeek-V4-Pro (0813) released?

It was released on August 12, 2026.

### How do I call DeepSeek-V4-Pro (0813)?

Send requests to RealRelay's OpenAI-compatible endpoint with the model ID baidu/deepseek-v4-pro-0813.