API Documentation

Base URL and Authentication

Your API key authenticates every request. We issue one active key per account, replacing the previous one if you generate a new key. Use the Authorization header with the Bearer scheme. The base URL for our claude opus nsfw uncensored service is https://api.claudeopusnsfwuncensored.com/v1. We do not offer embeddings or image generation, only text completions. Your key is shown immediately after signup via Google or email. No phone number is required.

First Request

Send a standard chat completion request to test connectivity. Replace YOUR_API_KEY with your actual key. The model ID is uncensored. This endpoint returns text only, with no audio or video. You can adjust the prompt length up to the context window limit. Our service does not track your prompts for training purposes. This simple call verifies that your authentication is correct.

Python SDK Integration

Use the official OpenAI Python client with a custom base URL. This approach works with our uncensored LLM API just as it does with other providers. Set the base_url parameter to our endpoint. The model name remains uncensored. You can stream responses or fetch them synchronously. This method requires no wrapper libraries. It keeps your code portable and simple.

Node SDK Integration

Integrate our API into your Node.js applications using the standard client. Configure the baseURL to point to our server. The API key goes in the apiKey field. This setup allows you to generate text without censorship for lawful adult content. The code structure mirrors the OpenAI SDK exactly. You can handle errors and retry logic using standard promises. This ensures reliable integration.

Streaming Responses

Enable streaming by setting stream: true in your request. The server sends chunks via Server-Sent Events. Each chunk contains partial text and token usage data. The final chunk includes the complete token count. This feature reduces perceived latency for long responses. You can parse chunks in real-time. Streaming works with both Python and Node clients. It provides a smoother user experience.

Limits, Errors, and Context

The context window is 100,000 tokens for input and output combined. Each request can output up to 16,000 tokens. You are limited to 300 requests per minute and 8 concurrent requests per key. A 401 error means your API key is invalid. A 402 error indicates insufficient credit. A 429 error signals that you have exceeded the rate limit. Errors are free, so you do not pay for failed requests. Your prepaid credit never expires.

cURL

Copycurl https://api.claudeopusnsfwuncensored.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Fix syntax error in Python function"}]
  }'

Python

Copyfrom openai import OpenAI

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

Node.js

Copyimport OpenAI from "openai";

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

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)