# DeepSeek V4 Pro

## Best for

A main coding agent paired with DeepSeek V4 Flash sub-agents

## When not to use

Image, audio, or video. Not the latency or cost pick — use V4 Flash (`dsv4`) or V4.1 Flash for sub-agents and high-volume steps.

## Overview

DeepSeek V4 Pro 0813 is a 1.7T-parameter open-weight model for complex coding work. A common setup is to use Pro for the main agent and V4 Flash 0731 for sub-agents. This keeps the whole coding workflow on open-weight models and can cost less than using closed frontier models.

| | |
| --- | --- |
| API identifier | `deepseek-v4-pro-0813` |
| 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 |
| --- | --- | --- |
| $1.04 | $0.04 | $2.08 |

## Call it

Put `deepseek-v4-pro-0813` 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": "deepseek-v4-pro-0813",
    "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).