Switch your client in three lines

Base URL and Authentication

Our service is a drop-in replacement for standard OpenAI endpoints. To authenticate, you need an API key, which you generate instantly on the Get API key page using Google or email. There is no phone number verification or credit card required for the initial trial credit of $0.50.

Configure your client to point to our base URL. Every request must include the Authorization: Bearer header with your unique key. This ensures your prompts are routed to our uncensored model without hitting external safety filters.

The base URL is: https://api.deepseeknsfw.top/v1. All standard OpenAI SDKs support this configuration via a simple base_url override. You can verify your connection by listing available models.

First Request

Send your first completion request using the /v1/chat/completions endpoint. This endpoint accepts standard chat format messages. The model ID to use is uncensored. This model is an open-weight large language model tuned for adult content and does not refuse lawful topics.

Below is a minimal cURL example to test connectivity and receive a text response. Ensure you replace YOUR_API_KEY with the key generated from your account dashboard.

If you receive a valid JSON response, your integration is working. If you see a 401 error, check that your key is correct. A 402 error indicates your prepaid credit has been exhausted.

Python SDK Integration

Using the official openai Python package makes integration trivial. Initialize the client with our base URL and your API key. You can then call chat.completions.create just as you would for GPT-4.

This approach works for any language that supports the OpenAI protocol. The model will return text output based on your prompt. Since we do not offer embeddings or image generation, stick to text completion tasks. The code below demonstrates a basic synchronous request.

Remember that our model ID is fixed at uncensored. You do not need to select a version; the API serves the latest uncensored weights by default.

Node.js SDK Setup

For JavaScript developers, the openai Node.js package works identically. Set the baseURL to our endpoint and provide your key in the apiKey field. This allows you to use the same client code you might have used for other providers, simply by changing the configuration.

Create a completion object with a system prompt and user message. The response will be available in response.choices[0].message.content. This method is reliable for generating long-form adult content or creative writing without refusal.

The code sample below shows how to instantiate the client and send a request. Ensure your environment supports the required Node.js version for the SDK you are using.

Streaming Responses

For better user experience, enable streaming by setting stream: true in your request. The API returns a Server-Sent Events (SSE) stream. Each chunk contains partial text and token usage information.

Streaming is ideal for chat interfaces where you want to display tokens as they are generated. The final chunk in the stream contains the total token usage for the request. This helps you track costs accurately, as we charge $0.25 per 1M input tokens and $1.00 per 1M output tokens.

Handle stream errors gracefully. If the connection drops, you may lose partial tokens. Our API ensures that completed tokens are billed correctly even if the stream ends unexpectedly.

Limits, Errors, and Context

Our API has strict limits to ensure stability. You are allowed 300 requests per minute per key and 8 concurrent requests. The maximum request body size is 8 MB. If you exceed the rate limit, you will receive a 429 error. Increase your wait time or reduce concurrency.

The context window is 100,000 tokens total (prompt + completion). The maximum output per request is 32,000 tokens, or 2,048 if you do not specify max_tokens. Errors and refusals are free, so you can test without draining your credit.

Common errors include 401 (invalid key), 402 (insufficient credit), and 429 (rate limit). Refunds are not available for credit, but mistakes like double charges are fixed via the Support page. Keep your key secure; only one key is active per account.

cURL

Copycurl https://api.deepseeknsfw.top/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."}]
  }'

Python

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.deepseeknsfw.top/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)

Node.js

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.deepseeknsfw.top/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);

Streaming

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)