DeepSeek API 快速入门与集成指南

DeepSeek API 概览

DeepSeek API 采用与 OpenAI 兼容的接口格式，开发者可以零成本迁移现有代码。同时提供 Anthropic API 兼容格式，支持多种集成方式。

基础配置

可用模型

Python 快速开始

使用 OpenAI SDK

from openai import OpenAI

client = OpenAI(
    api_key="your-deepseek-api-key",
    base_url="https://api.deepseek.com"
)

# 非流式调用
response = client.chat.completions.create(
    model="deepseek-v4-pro",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"}
    ],
    stream=False
)
print(response.choices[0].message.content)

思考模式

response = client.chat.completions.create(
    model="deepseek-v4-pro",
    messages=[
        {"role": "user", "content": "求解：x^2 + 5x + 6 = 0"}
    ],
    thinking={"type": "enabled"},
    reasoning_effort="high",  # low/medium/high
    stream=False
)

流式输出

stream = client.chat.completions.create(
    model="deepseek-v4-pro",
    messages=[{"role": "user", "content": "写一首关于春天的诗"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

cURL 调用

curl https://api.deepseek.com/chat/completions 
 -H "Content-Type: application/json" 
 -H "Authorization: Bearer $DEEPSEEK_API_KEY" 
 -d '{
   "model": "deepseek-v4-pro",
   "messages": [
     {"role": "system", "content": "You are a helpful assistant."},
     {"role": "user", "content": "Hello!"}
   ],
   "thinking": {"type": "enabled"},
   "reasoning_effort": "high",
   "stream": false
 }'

Agent 工具集成

DeepSeek API 已被主流 AI Agent 工具支持，无需编码即可使用：

• Claude Code — 配置自定义API端点
• GitHub Copilot — 选择 DeepSeek 作为后端模型
• OpenCode — 直接支持 DeepSeek
• One API — 通过渠道配置接入

定价

相比 OpenAI 同级别模型，DeepSeek 的定价低 80-90%。