DeepSeek V4 多模态能力指南
2026-05-13
·
DeepSeek
## DeepSeek V4 多模态能力指南
### 支持的模态
DeepSeek V4 系列支持以下多模态输入：
- 纯文本
- 文本 + 图片
- 文本 + 图片 + 音频
### 图片输入示例
```python
from openai import OpenAI
client = OpenAI(base_url="https://api.deepseek.com/v1", api_key="your-key")
response = client.chat.completions.create(
model="deepseek-v4-pro",
messages=[
{
"role": "user",
"content": [
{"type": "text", "text": "描述这张图片"},
{"type": "image_url", "image_url": {"url": "https://example.com/image.jpg"}}
]
}
]
)
print(response.choices[0].message.content)
```
### 函数调用
```python
tools = [{
"type": "function",
"function": {
"name": "get_weather",
"description": "获取天气",
"parameters": {
"type": "object",
"properties": {
"city": {"type": "string", "description": "城市名"}
},
"required": ["city"]
}
}
}]
response = client.chat.completions.create(
model="deepseek-v4-pro",
messages=[{"role": "user", "content": "北京天气怎么样"}],
tools=tools,
tool_choice="auto"
)
```
### 注意事项
- V4 系列兼容 OpenAI 和 Anthropic 双协议
- deepseek-chat 和 deepseek-reasoner 将于2026年7月24日退役
- 新 model ID：deepseek-v4-flash / deepseek-v4-pro
评论区
该文章暂未开放评论功能。