# DeepSeek V4 Flash 0731

Re-post-trained GA release of DeepSeek V4 Flash optimized for fast, economical coding, reasoning, and agent workflows.

## Overview

- **Provider:** DeepSeek
- **Model ID:** `deepseek-v4-flash-0731`
- **Type:** Chat
- **Canonical URL:** https://modelstack.cc/models/chat/deepseek-v4-flash-0731
- **Version:** V4 Flash 0731
- **Best for:** Fast agentic coding, tool use, reasoning, high-volume workloads

## Pricing

| Usage | Price |
| --- | ---: |
| Input | $0.14 / 1M tokens |
| Output | $0.28 / 1M tokens |
| Cache read | $0.028 / 1M tokens |
| Cache write (5 minutes) | $0.14 / 1M tokens |

## Specifications

- **Context window:** 1M
- **Maximum output:** 384K
- **Released:** 2026-07-31

## Capabilities

- chat
- tool_use
- reasoning
- coding
- analysis

## API usage

Use this model ID in a ModelStack API request:

```json
{
  "model": "deepseek-v4-flash-0731"
}
```

For the rendered page, visit https://modelstack.cc/models/chat/deepseek-v4-flash-0731.