Unrestricted Claude Quickstart

Base URL and Authentication

The API lives at https://api.unrestrictedclaude.com/v1. You authenticate with a bearer token sent in the Authorization header. Sign up with Google or email on the key page to get your credential instantly. No phone number is required. Your prompts are not used for training. The endpoint accepts standard JSON payloads for chat completions.

Send Your First Request

Make a POST request to /v1/chat/completions with your model ID uncensored. The system processes text input and returns text output. You can send up to 8MB per request. Errors do not consume your prepaid credit. Refusals are also free. This direct approach keeps your workflow simple and transparent.

Copycurl https://api.unrestrictedclaude.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the top 5 npm packages for date formatting."}]
  }'

Python SDK Integration

Use the official OpenAI Python library to connect. Set the base URL to our endpoint and provide your API key. The model ID remains uncensored. This works with any standard OpenAI-compatible client. You get raw freedom without extra configuration steps. The code runs exactly as you expect.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.unrestrictedclaude.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 SDK Setup

Install the OpenAI Node SDK and point it to our base URL. Pass your key in the configuration object. The model ID is still uncensored. This approach lets you build clients for Telegram or other platforms quickly. The integration is straightforward. You avoid the friction of custom HTTP clients.

Copyimport OpenAI from "openai";

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

Enable Streaming

Set the stream parameter to true for real-time output. You receive server-sent events (SSE) as tokens are generated. The final chunk includes the total token usage statistics. This is ideal for chat interfaces that need instant feedback. You do not wait for the full response to complete. The experience feels native.

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)

Limits, Errors, and Context

Each key allows 300 requests per minute and 8 concurrent requests. The context window is 100,000 tokens for prompt and completion combined. You get a 401 error if the key is invalid. A 402 error means you have no credit. A 429 error indicates you hit the rate limit. The model supports function calling and JSON mode. Max output is 16,000 tokens per request.