How to Get a DeepSeek API Key: A Step-by-Step Guide

Reynaldi Chernando

Updated: March 10, 2026

On this page

Prerequisites Step 1: Create Your DeepSeek Account Step 2: Generate Your API Key Step 3: Make Your First API Call One API Key, Hundreds of Models Conclusion Related

In this guide, you'll learn how to get your DeepSeek API key. You'll create a DeepSeek account, generate your key, and make your first API call. We'll also show you a simpler alternative if you want access to hundreds of AI models without managing multiple accounts.

Prerequisites

An email address or phone number
A payment method — DeepSeek's API is usage-based
Basic familiarity with code (we'll show simple JavaScript examples)

Step 1: Create Your DeepSeek Account

Go to platform.deepseek.com. This is the API platform where you manage your keys, billing, and usage.

Before your API key will work, you need to add a payment method and top up your balance. Go to Top up and add credits. DeepSeek charges per token, and pricing varies by model.

Step 2: Generate Your API Key

In the left sidebar, click API keys, then click Create new API key.

Give your key a descriptive name like my-app-dev so you can identify it later, then confirm.

Important: Copy the key immediately. DeepSeek only shows it once. If you lose it, you'll need to generate a new one.

Store it somewhere safe — a password manager, an .env file, or your platform's secrets manager. Never commit API keys to a public repository.

DeepSeek API key revealed with copy button

Step 3: Make Your First API Call

DeepSeek uses an OpenAI-compatible API, so you can use the OpenAI SDK directly. Install it first:

npm install openai

Then make your first call:

import OpenAI from "openai";

const openai = new OpenAI({
  baseURL: "https://api.deepseek.com",
  apiKey: process.env.DEEPSEEK_API_KEY,
});

const completion = await openai.chat.completions.create({
  model: "deepseek-chat",
  messages: [{ role: "user", content: "Hello, world!" }],
});

console.log(completion.choices[0].message.content);

If you get a response back, everything is working. For more details, check out DeepSeek's API documentation.

One API Key, Hundreds of Models

The process above works well for DeepSeek specifically — but what happens when you want to use GPT, Claude, Gemini, Llama, Mistral, or any of the other major models?

You'd need to repeat the entire process for each provider: create an account, set up billing, generate and manage a separate key. That's a lot of overhead, especially if you're experimenting or building something that uses multiple models.

Puter offers a simpler approach: one account, one auth token, access to hundreds of models across providers.

Instead of managing five different API dashboards, you point your existing code to Puter's OpenAI-compatible endpoint and use your Puter auth token:

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.puter.com/puterai/openai/v1/",
  apiKey: "YOUR_PUTER_AUTH_TOKEN",
});

const response = await client.chat.completions.create({
  model: "deepseek-chat", // or claude-sonnet-4-6, gpt-5-nano, gemini-2.5-flash-lite, etc.
  messages: [{ role: "user", content: "Hello, world!" }],
});

console.log(response.choices[0].message.content);

Since DeepSeek already uses the OpenAI-compatible format, switching to Puter is especially easy — just change the baseURL and apiKey.

To get your Puter auth token, create a free account at puter.com, then go to puter.com/dashboard and click Copy to grab your token.

Conclusion

You now know how to create a DeepSeek account, generate an API key, and make your first API call. For a deeper dive, check out DeepSeek's official API docs.

Free, Serverless AI and Cloud

Start creating powerful web applications with Puter.js in seconds!

Get Started Now

Read the Docs • Try the Playground