Your First Step with DeepSeek API: A Quick Start Guide

DeepSeek API offers powerful AI capabilities accessible through a format compatible with OpenAI. This means you can leverage existing OpenAI SDKs and tools with minor configuration adjustments to tap into DeepSeek's potential. This guide provides a walkthrough for making your first API call, empowering you to quickly start building applications with DeepSeek.

Understanding DeepSeek API Compatibility

One of the key advantages of DeepSeek API is its design for seamless integration with the OpenAI ecosystem. Instead of learning a completely new system, developers familiar with OpenAI can quickly adapt. Here’s what you need to know:

• OpenAI Compatibility: DeepSeek API is designed to be compatible with the OpenAI API format.
• SDK Flexibility: You can use the OpenAI SDK or software compatible with the OpenAI API to access DeepSeek.
• Configuration is Key: By modifying the base URL and API key, you can redirect your existing OpenAI-based code to DeepSeek.

Essential Parameters

To begin using the DeepSeek API, you'll need two crucial parameters:

Important Notes:

• The v1 in the alternate base_url has no relationship with the model's version.
• The deepseek-chat model has been upgraded to DeepSeek-V3. The API remains unchanged. You can invoke DeepSeek-V3 by specifying model='deepseek-chat'.
• deepseek-reasoner is the latest reasoning model, DeepSeek-R1. Invoke it by specifying model='deepseek-reasoner'.

Making Your First API Call

Once you have your API key, you can use various programming languages to interact with the DeepSeek API. Here are examples using curl, Python, and Node.js.

Example 1: 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
  }'

Example 2: Using Python

# Please install OpenAI SDK first: `pip3 install openai`
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)

Example 3: Using Node.js

// Please install OpenAI SDK first: `npm install openai`
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();

These examples demonstrate a basic, non-streaming request. For real-time applications, you can set the stream parameter to true to receive streaming responses.

Exploring Further

Congratulations, you've made your first API call to DeepSeek! Now you can start digging deeper:

• Models and Pricing: Understand DeepSeek's model options and pricing structure to optimize your usage.
• Reasoning Model: Discover the power of the reasoning model.

By understanding the compatibility, essential parameters, and basic API calls, you're now equipped to start building innovative applications with DeepSeek.