Getting Started with DeepSeek API: A Quick Guide

DeepSeek API Overview

DeepSeek API uses an OpenAI-compatible API format, which means you can access the DeepSeek API using the OpenAI SDK or any OpenAI API-compatible software with simple configuration changes. This guide will help you get started with DeepSeek API quickly.

Basic Configuration Parameters

Key configuration parameters include:

base_url: https://api.deepseek.com
- For OpenAI compatibility, you can also use https://api.deepseek.com/v1
- Note: The v1 here is unrelated to model versions
api_key: Required (needs to be applied for)
model: Use deepseek-chat to access the latest DeepSeek-V3 model

API Usage Examples

Using curl

curl https://api.deepseek.com/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <DeepSeek API Key>" \
  -d '{
        "model": "deepseek-chat",
        "messages": [
          {"role": "system", "content": "You are a helpful assistant."},
          {"role": "user", "content": "Hello!"}
        ],
        "stream": false
      }'

Using Python SDK

from openai import OpenAI

client = OpenAI(api_key="<DeepSeek API Key>", base_url="https://api.deepseek.com")

response = client.chat.completions.create(
    model="deepseek-chat",
    messages=[
        {"role": "system", "content": "You are a helpful assistant"},
        {"role": "user", "content": "Hello"},
    ],
    stream=False
)

print(response.choices[0].message.content)

Using Node.js SDK

import OpenAI from "openai";

const openai = new OpenAI({
  baseURL: "https://api.deepseek.com",
  apiKey: "<DeepSeek API Key>",
});

async function main() {
  const completion = await openai.chat.completions.create({
    messages: [{ role: "system", content: "You are a helpful assistant." }],
    model: "deepseek-chat",
  });

  console.log(completion.choices[0].message.content);
}

main();

Important Notes

Before getting started, ensure you have:
- Applied for a DeepSeek API key
- Installed the appropriate SDK (e.g., pip install openai for Python, npm install openai for Node.js)
Streaming Output:
- Non-streaming by default
- Enable streaming by setting stream=true
- Streaming is ideal for real-time response scenarios
Model Information:
- The deepseek-chat model has been fully upgraded to DeepSeek-V3
- The interface remains unchanged, no code modifications needed
- Access the latest version by specifying model='deepseek-chat'

Next Steps

After completing the basic setup, you can:

Explore advanced API parameters
Implement streaming functionality
Integrate into your applications
Optimize API call efficiency

You're now ready to start building your AI applications with DeepSeek API!