# DeepSeek V4 Flash

## Best for

Low-cost text agents with long prompts and reusable prefixes

## When not to use

Image, audio, or video — this identifier is text only. Choose DeepSeek V4.1 Flash when you need native images, or V4 Pro when a main coding agent needs more depth.

## Overview

DeepSeek V4 Flash 0731 is the smaller, more efficient member of the DeepSeek V4 family. It has 284B total parameters, with 13B active per token, and a 1,048,576-token context window. Hybrid attention helps keep long prompts cheaper to process. You can also adjust reasoning effort to trade speed and token use for more deliberate answers.

| | |
| --- | --- |
| API identifier | `dsv4` |
| Developer | DeepSeek |
| Context window | 1,048,576 tokens |
| Supports | text, reasoning, tool-use |
| Status | Serving |

## Rates

USD per 1M tokens, on-demand tier.

| Input | Cached input | Output |
| --- | --- | --- |
| $0.04 | $0.02 | $0.21 |

## Call it

Put `dsv4` in the `model` field. The same request works against the Anthropic Messages API — see [API Compatibility](https://inference.boundless.network/docs/api-compatibility).

```bash
curl https://api.inference.boundless.network/v1/chat/completions \
  -H "Authorization: Bearer $BOUNDLESS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "dsv4",
    "messages": [{
      "content": "Say hello",
      "role": "user"
    }]
  }'
```

Every model we serve is listed at [Models](https://inference.boundless.network/models); the rate card in full is on [Pricing](https://inference.boundless.network/docs/pricing).