# deepseek-v4-pro

DeepSeek V4 Pro is a large-scale mixture-of-experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with hybrid attention for efficient long-context processing. It accepts text only and supports tool calling and structured outputs.

DeepSeek V4 Pro 是 DeepSeek 的大规模混合专家模型，总参数 1.6 万亿、激活 490 亿，上下文 100 万 token。面向高阶推理、编程和长程智能体，采用混合注意力处理长上下文。只接受文本，支持工具调用和结构化输出。

- Provider: DeepSeek
- Billing Mode: Time-of-day pricing
- Label: 学术, 金融, 医疗, 法律, 营销, 搜索优化, 编程, 角色扮演, 科学, 技术, 翻译, 百科
- Model ID: `deepseek-v4-pro`
- Web: https://en.llmoxy.com/models/deepseek-v4-pro

## Pricing

Prices are in Chinese yuan (CNY, ￥); pay-as-you-go prices are per 1M tokens.

Token Group: Deepseek

| Tier | In | Out | Cache read |
| --- | --- | --- | --- |
| Weekdays 09:00–12:00, 14:00–18:00 (Beijing time) | ￥0.528 | ￥1.58 | ￥0.0176 |
| Other hours | ￥0.264 | ￥0.792 | ￥0.0088 |

That is 94% below the official API price.

## Quick start

Set the LLMOXY_KEY environment variable to your API key before running.

### cURL

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

### Python

```python
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://llmoxy.com/v1",
    api_key=os.environ["LLMOXY_KEY"],
)

resp = client.chat.completions.create(
    model="deepseek-v4-pro",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)
```

### Node.js

```javascript
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://llmoxy.com/v1",
  apiKey: process.env.LLMOXY_KEY,
});

const resp = await client.chat.completions.create({
  model: "deepseek-v4-pro",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(resp.choices[0].message.content);
```

## Endpoints

- Chat Completions: `POST https://llmoxy.com/v1/chat/completions`

## FAQ

### How much does deepseek-v4-pro cost on LLMoxy?

Time-of-day pricing. Price in the “Deepseek” token group: From In ￥0.264 / 1M. That is 94% below the official API price.

### How do I call deepseek-v4-pro?

Create an API key in the LLMoxy console, set model to deepseek-v4-pro, and send the request to: Chat Completions POST https://llmoxy.com/v1/chat/completions. You can also use the OpenAI SDK directly with the base URL set to https://llmoxy.com/v1.

### Which token groups can I use with deepseek-v4-pro?

The token group sets the price you pay: you pick a group when you create an API key in the console, and every call made with that key is billed at that group’s price. Groups available for deepseek-v4-pro: Deepseek.

### Do I need an international credit card?

No. Top up your balance in the console first; each call is then deducted from the balance based on actual usage. Payment methods: Alipay, WeChat Pay, Visa / MasterCard, Apple Pay, and crypto such as USDT, BTC, SOL, and TRX. Multi-currency support.

## More from DeepSeek

- [deepseek-v4-flash](https://en.llmoxy.com/models/deepseek-v4-flash.md): From In ￥0.06 / 1M
- [deepseek-v4-flash-0731](https://en.llmoxy.com/models/deepseek-v4-flash-0731.md): From In ￥0.06 / 1M
- [deepseek-v4-pro-0813](https://en.llmoxy.com/models/deepseek-v4-pro-0813.md): From In ￥0.264 / 1M
- [deepseek-v4.1-flash](https://en.llmoxy.com/models/deepseek-v4.1-flash.md): From In ￥0.06 / 1M

## Links

- [All model prices](https://en.llmoxy.com/pricing.md)
- [Documentation](https://en.llmoxy.com/docs/api-reference/api-overview.md)
- [llms.txt](https://en.llmoxy.com/llms.txt)

This is the markdown version of https://en.llmoxy.com/models/deepseek-v4-pro.
