DeepSeek V4 API: First request in five minutes

Authentication & Base URL

Our API uses standard API key authentication. You can generate a key instantly on the Get API key page by entering your email and password. No credit card is required for the trial, which includes $0.50 in valid credit for 7 days. Once you have your key, configure your client to use our base URL: https://api.deepseek4api.com/v1.

Set the Authorization header to Bearer YOUR_API_KEY. This base URL works with any OpenAI-compatible SDK. The model identifier you must specify in your requests is uncensored. This ensures you are interacting with our open-weight model tuned for unrestricted responses, rather than any vendor-specific variant.

Basic Chat Completion

Send a standard chat completion request to generate text. The API accepts a list of messages containing role and content fields. Below is a basic cURL example demonstrating a simple text query. This works for any OpenAI-compatible client by adjusting the base URL and model ID.

Copycurl https://api.deepseek4api.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
  }'

Replace YOUR_API_KEY with your generated key. The response will contain a standard choices array with the generated text. Note that this endpoint supports tool/function calling, allowing you to integrate structured outputs into your applications.

Python SDK Integration

Use the official OpenAI Python SDK to interact with our API. Configure the client with our base URL and your API key. The model name is uncensored. This approach lets you keep your existing client code while switching the backend model.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.deepseek4api.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Ensure you have the openai package installed. The code above demonstrates a synchronous request. For asynchronous applications, you can use the AsyncOpenAI client with the same configuration. This method is ideal for backend services where you need reliable, non-streaming text generation.

Node SDK Usage

For Node.js applications, use the openai npm package. Initialize the client with the baseURL pointing to our service and provide your API key. The model identifier remains uncensored.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.deepseek4api.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

This setup allows you to integrate uncensored LLM capabilities into your JavaScript or TypeScript projects. The SDK handles the JSON serialization and HTTP requests automatically. You can extend this basic setup to include tools or function calling if your application requires structured data outputs.

Streaming Responses

For real-time text generation, enable streaming in your client. Set stream: true in your request parameters. The API returns Server-Sent Events (SSE), allowing you to process tokens as they are generated. This reduces perceived latency for end-users.

Copystream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Handle the stream events in your code to display text incrementally. Streaming works with both Python and Node SDKs. Ensure your client properly closes the stream connection when the response is complete or if an error occurs. This feature is essential for chat interfaces where immediate feedback is critical.

Limits, Errors & Context

The API enforces a 100,000 token context window for both prompt and completion combined. Request bodies must not exceed 8 MB. You are limited to 300 requests per minute per API key. If you exceed this limit, you will receive a 429 rate limit error.

Authentication errors return 401 if the key is invalid. Billing errors return 402 if your prepaid credit is exhausted. Unlike subscriptions, our pay-as-go credits never expire. Regenerate your key at any time from the dashboard, which instantly revokes the old key. This ensures secure access management without downtime.