Getting Started with DeepSeek API: Your First API Call

DeepSeek API offers powerful language models accessible through a user-friendly API format compatible with OpenAI. This compatibility allows developers to leverage existing OpenAI SDKs and software, streamlining the integration process. This article will guide you through making your first API call to the DeepSeek API.

DeepSeek API: Compatibility and Key Features

The DeepSeek API is designed to be easily integrated into your projects. Thanks to its OpenAI-compatible format, developers can quickly adapt their existing workflows to utilize DeepSeek's advanced language models.

Here's what you need to know:

• OpenAI Compatibility: Use your existing OpenAI SDKs and software with minor configuration changes.
• Base URL: The primary base URL for the DeepSeek API is https://api.deepseek.com. You can also use https://api.deepseek.com/v1 for OpenAI compatibility. Note that the /v1 does not correspond to the model version.
• API Key: You'll need an API key to access the DeepSeek API. You can obtain one from the DeepSeek Platform.
• DeepSeek-V3: The deepseek-chat model has been upgraded to DeepSeek-V3. The API remains unchanged. Invoke DeepSeek-V3 by specifying model='deepseek-chat'.
• Reasoning Model deepseek-reasoner is the latest reasoning model, DeepSeek-R1. Invoke DeepSeek-R1 by specifying model='deepseek-reasoner'.

Making Your First API Call

Once you have your API key, you can start making requests to the DeepSeek API. The following examples demonstrate how to invoke the Chat API using curl, Python, and NodeJS.

Essential Parameters:

Before diving into the code, here are the key parameters you'll need:

• base_url: https://api.deepseek.com
• api_key: Your unique API key obtained from the DeepSeek platform.

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 request to the /chat/completions endpoint with a simple conversation. Replace <DeepSeek API Key> with your actual API key. The "stream": false parameter indicates that the API should return the complete response at once, as opposed to streaming it.

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)

This Python script utilizes the OpenAI SDK. Remember to install the OpenAI library before running this code using pip3 install openai. Again, replace <DeepSeek API Key> with your actual API key.

3. Using NodeJS

// 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();

This NodeJS example also uses the OpenAI SDK. Install it with npm install openai. Replace <DeepSeek API Key> with your actual API key.

Exploring Further

Congratulations on making your first API call to the DeepSeek API! Now that you've successfully connected, consider exploring these next steps:

• Models & Pricing: Understand the different DeepSeek models and their associated costs.
• Reasoning Model: Learn about the reasoning model, DeepSeek-R1.
• The Temperature Parameter: Control the randomness of your reponses with the temperature parameter.
• API Guides: Dive deeper into specific use cases with the API Guides, covering topics like multi-round conversations, JSON output, and function calling.
• Error Codes: Familiarize yourself with potential error codes for effective debugging.

By leveraging the DeepSeek API's power and flexibility, you can create innovative applications and experiences. This guide provides a starting point for your journey with DeepSeek's language models.