Your First API Call: A Quick Guide to Using the DeepSeek API

The DeepSeek API is designed to be user-friendly and compatible with the OpenAI API format, which allows developers to integrate it seamlessly into existing workflows. This guide will walk you through making your first API call, explaining the necessary configurations and providing example scripts in various programming languages.

Understanding DeepSeek API Compatibility

One of the key advantages of the DeepSeek API is its compatibility with OpenAI. If you're already familiar with OpenAI's SDK or other tools, you can easily adapt them to work with DeepSeek by modifying the base URL.

Essential Parameters for Your First API Call

Before diving into the code, you'll need two essential parameters:

• base_url: This is the API endpoint. Use https://api.deepseek.com. For OpenAI compatibility, you can also use https://api.deepseek.com/v1.
• api_key: You'll need an API key to authenticate your requests. You can apply for one on the DeepSeek Platform.

Invoking the Chat API: Step-by-Step Examples

Once you have your API key, you can start making requests to the DeepSeek API. Here are examples using curl, Python, and Node.js to invoke the chat API:

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
  }'

• This command sends a POST request to the /chat/completions endpoint.
• It includes the Content-Type and Authorization headers. Make sure to replace “<DeepSeek API Key>” with your actual API key.
• The -d flag provides the JSON payload, specifying the model, messages, and stream parameter.

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)

• First, install the OpenAI SDK using pip3 install openai.
• Import the OpenAI class and initialize it with your API key and the DeepSeek base URL.
• Use the chat.completions.create method to send your request, specifying the model, messages, and stream parameter.
• The response will contain the model's reply, which you can access via response.choices[0].message.content.

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();

• Install the OpenAI SDK using npm install openai.
• Import the OpenAI class and configure it with your API key and the DeepSeek base URL.
• Use the chat.completions.create method within an async function to send your request.
• The response will contain the model's reply, accessible via completion.choices[0].message.content.

Key Considerations and Model Information

• Model Versions: The deepseek-chat model has been upgraded to DeepSeek-V3. You can invoke it by specifying model='deepseek-chat'.
• Reasoning Model: deepseek-reasoner is the latest reasoning model, DeepSeek-R1. You can invoke DeepSeek-R1 by specifying model='deepseek-reasoner'. See more about Reasoning Models.
• Streaming: The examples above are non-streaming. To receive a stream response, set the stream parameter to true.

By following this guide, you should be able to successfully make your first API call to the DeepSeek API. Explore the DeepSeek API documentation for more advanced features and models. Don't forget to check out the API status page for updates and maintenance information.