Getting Started with DeepSeek API: Your First API Call

DeepSeek API offers a powerful suite of tools for developers looking to integrate advanced AI capabilities into their applications. This article will guide you through making your first API call, providing a practical introduction to using the DeepSeek API.

Understanding DeepSeek's Compatibility

The DeepSeek API is designed to be compatible with the OpenAI API format. This means you can leverage existing OpenAI SDKs and tools with minimal configuration changes, making the transition smooth and efficient.

Setting Up Your Environment

Before making your first call, you'll need a few things:

• An API Key: Obtain an API key from the DeepSeek Platform.
• Base URL: The base URL for the DeepSeek API is https://api.deepseek.com. You can also use https://api.deepseek.com/v1 for OpenAI compatibility.

Making Your First API Call

Here's how to make a basic API call to the DeepSeek chat endpoint using curl, Python, and Node.js.

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

# 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)

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();

Key Parameters Explained

• base_url: Specifies the API endpoint (https://api.deepseek.com).
• api_key: Your unique API key for authentication.
• model: Specifies the model to use (e.g., deepseek-chat).
• messages: An array containing the conversation history.
• stream: A boolean value. Set to true for streaming responses.

Exploring DeepSeek Models

DeepSeek offers a range of models tailored for different tasks:

• deepseek-chat: is now upgraded to DeepSeek-V3. Invoke DeepSeek-V3 by specifying model='deepseek-chat'.
• deepseek-reasoner: DeepSeek-R1, released by DeepSeek, is the latest reasoning model. Invoke DeepSeek-R1 by specifying model='deepseek-reasoner'.

Additional Resources

• API Reference: See the API Reference for detailed information on all available endpoints and parameters.
• Guides: Explore the API Guides for specific use cases like reasoning models and multi-round conversations.
• FAQ: Find answers to common questions in the FAQ.
• Pricing: Understand the costs associated with using the API by reviewing the Models & Pricing.

By following this guide, you should be well-equipped to make your first API call to the DeepSeek API and begin exploring its capabilities.