Hi there! If you're looking to install Deepseek in your project, you're in the right place. In this guide, I'll walk you through the process of installing Deepseek using NPM in just a few simple steps. Additionally, I'll cover how to use CURL and integrate Deepseek with Python.
Deepseek is an open-source large language model (LLM) developed by Hangzhou DeepSeek Artificial Intelligence Co., Ltd., a Chinese AI company.
Despite being created at a significantly lower cost (just $6 million compared to OpenAI's $100 million for GPT-4), Deepseek performs tasks at the same level as ChatGPT.
The model was developed during U.S. sanctions on Nvidia chips, which aimed to limit China's AI development. On January 10, 2025, the company launched its first free chatbot app for iOS and Android.
By January 27, it had become the most-downloaded free app on the iOS App Store in the U.S. also you can download from Play Store, even impacting Nvidia's stock price with an 18% drop.
The DeepSeek API uses a format that is fully compatible with the OpenAI API. By adjusting the configuration settings, you can seamlessly use the OpenAI SDK or any software compatible with the OpenAI API to access the DeepSeek API.
PARAM | VALUE |
---|---|
base_url * | https://api.deepseek.com |
api_key | API KEY |
To ensure compatibility with OpenAI, you can use https://api.deepseek.com/v1 as the base_url. However, please note that the v1 in the URL does not correspond to the model's version in any way.
The prices listed below are in unites of per 1M tokens. A token, the smallest unit of text that the model recognizes, can be a word, a number, or even a punctuation mark.
Pricing Details:
MODEL | CONTEXT LENGTH | MAX COT TOKENS | MAX OUTPUT TOKENS | 1M TOKENS INPUT PRICE (CACHE HIT) |
1M TOKENS INPUT PRICE (CACHE MISS) |
1M TOKENS OUTPUT PRICE |
---|---|---|---|---|---|---|
deepseek-chat | 64K | - | 8K | $0.014 | $0.14 | $0.28 |
deepseek-reasoner | 64K | 32K | 8K | $0.14 | $0.55 | $2.19 |
After obtaining an API key, you can access the DeepSeek API using the example scripts provided below:
We'll install openai using the following npm command. And we'll use deepseek API using the following example.
npm install openai
Example:
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: "Install deepseek using npm" }],
model: "deepseek-chat",
});
console.log(completion.choices[0].message.content);
}
main();
Next, we'll see how to use deepseek using the CURL method:
Example:
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": "Install deepseek using CURL"},
{"role": "user", "content": "Hello!"}
],
"stream": false
}'
Then, we'll install using the pip3 command in Python:
pip3 install openai
Example:
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": "Install deepseek using python"},
{"role": "user", "content": "Hello"},
],
stream=False
)
print(response.choices[0].message.content)
You might also like: