Getting Started with the DeepSeek API: Your First API Call

The DeepSeek API offers powerful AI capabilities, and getting started is surprisingly straightforward. This guide will walk you through making your first API call, leveraging DeepSeek's compatibility with the OpenAI API format. By the end, you'll be equipped to integrate DeepSeek's models into your projects.

DeepSeek API: OpenAI Compatibility

One of the key advantages of the DeepSeek API is its compatibility with the OpenAI API format. This means you can often use existing OpenAI SDKs and software with minimal modification to access DeepSeek's functionalities. This compatibility reduces the learning curve and allows for a seamless transition for developers already familiar with OpenAI.

Configuration Essentials

Before making your first API call, you'll need two essential pieces of information:

• Base URL: https://api.deepseek.com (You can also use https://api.deepseek.com/v1 for OpenAI compatibility)
• API Key: You can apply for an API key on the DeepSeek Platform.

Important Considerations:

• While you can use https://api.deepseek.com/v1 for compatibility, the /v1 in this URL does not reflect the model's version.
• The deepseek-chat model is powered by DeepSeek-V3. Invoke it by specifying model='deepseek-chat'.
• For reasoning tasks, use deepseek-reasoner to access DeepSeek-R1, the latest reasoning model from DeepSeek.

Making Your First API Call with the Chat API

Once you have your API key, you can use various methods to interact with the DeepSeek API. Below are examples using curl, Python, and Node.js. These examples demonstrate a non-streaming request. For streaming responses, simply set the stream parameter to true.

Method 1: 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
  }'

Method 2: Python (using OpenAI SDK)

First, install the OpenAI SDK:

pip3 install openai

Then, use the following script:

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)

Method 3: Node.js (using OpenAI SDK)

First, install the OpenAI SDK:

npm install openai

Then, use the following script:

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();

Next Steps

Congratulations! You've successfully made your first API call to the DeepSeek API. Explore additional quick start resources:

• Models & Pricing: Understand the different DeepSeek models and their associated costs.
• The Temperature Parameter: Learn how to control the randomness and creativity of the model's responses.
• API Reference: Discover all available API endpoints.

By leveraging DeepSeek's API, users can start integrating state-of-the-art AI models into their workflows. For more advanced use cases, explore features like Function Calling and Context Caching. This will allow one to fully utilize every capability DeepSeek unlocks.