Privacy-first LLM API

Unrestricted Claude: The Uncensored API

Get an uncensored LLM API with a 100,000-token context window, no credit card required, and direct crypto payments for true unrestricted access.

Claim trial key View documentation

Test with one call

curl 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."}]
  }'

from 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)

import 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);

No card needed for trial
Crypto payments only
100k token context

$0.15per 1M input tokens

$0.50Output tokens / 1M

100,000token context

$0.50trial credit

300requests per minute

Core capabilities

OpenAI-compatible

Drop into existing code using standard chat-completions endpoints with zero friction.

Raw Freedom

Lawful adult content passes through without the typical polite refusals or filtering.

Zero Training Data

Your prompts remain private and are never used to train the underlying model.

Function Calling

Supports tools, JSON mode, and streaming via SSE for complex application logic.

No Subscriptions

Pay only for real token usage with prepaid credit that never expires.

Fast Performance

Optimized serving infrastructure delivers low-latency responses for high-volume developer workflows.

Setup guide

Uncensored API, real tokens

Create Account
Sign in with Google or email to get an immediate API key.
Top Up Crypto
Add funds via USDT or USDC to start using your allocated credit.
Make Requests
Send POST requests to our API endpoint and receive text responses instantly.

Build with it

Uncensored Chatbots

Build Telegram or Discord bots that answer freely without content filters.

Code Generation

Use unrestricted models for coding tasks without interruptions from safety guards.

Data Extraction

Parse large documents efficiently using the 100,000-token context window support.

Content Creation

Generate adult or controversial fiction without worrying about arbitrary topic bans.

Cost examples: see exactly what $1 buys you in tokens

$1 buys 6,666 input tokens and 2,000 output tokens. Input costs $0.15 per 1M tokens, so you get 66,666 input tokens per dollar. Output costs $0.50 per 1M tokens, yielding 2,000 output tokens per dollar. With a 16,000 token max response, this covers eight full responses. Errors are free.

Get an API key in seconds and start sending requests immediately.

Sign up: Use Google or email to create your account. No phone number required.
Get your key: Your API key appears instantly on the dashboard.
Send requests: Use the standard /v1/chat/completions endpoint with your preferred SDK.

Start with $0.50 trial credit. Top up with USDT or USDC later.

Unrestricted Claude: use cases for uncensored generation

We deliver raw, unfiltered model responses ideal for content creation and research. This uncensored LLM skips the polite refusals that break your workflows.

NSFW Storytelling

Generate adult fiction without sudden topic blocks. Writers keep their narrative voice intact.

Sensitive Code Review

Get direct analysis of proprietary logic. The model discusses security risks without corporate hesitation.

Open-Ended Brainstorming

Prompt freely. You get full creative freedom for every idea.

Checklist: how to pick the right uncensored provider

Verify the model is independent, not a proxy reselling known vendor outputs. Ensure payments use crypto only, preserving your financial privacy. Confirm context windows support at least 100k tokens for deep analysis. Check that streaming via SSE returns token usage in the final chunk. Avoid providers forcing subscriptions; prefer prepaid credit that never expires. Finally, test if the API is truly OpenAI-compatible for easy SDK integration.

Developers ask: real questions from the community

Can you use this for code? Yes, but scope directories carefully; never let the API access your backup drives directly. Is it fast? Many report speeds comparable to Opus with zero refusals. Does it work with Telegram bots? Absolutely; the OpenAI-compatible endpoint integrates instantly. What about privacy? We do not train on your prompts. Is there a free tier? New accounts receive $0.50 in trial credit for seven days, requiring only an email address.

How we differ from typical alternatives

We run our own tuned model, not a proxy reselling known vendors. This means no hidden rate limits or sudden model swaps. You get direct, uncensored answers for lawful adult use without content refusals. Our pricing is transparent: $0.15 per million input tokens and $0.50 for output. Errors are free. No subscription fees. You pay only for real tokens used.

Frequently asked questions

What is unrestricted claude and how does it differ from standard models?

It is an uncensored LLM API tuned to answer without refusals for lawful adult use. We run our own tuned model, not a resold vendor model. Context windows reach 100,000 tokens with streaming support for real-time usage tracking.

What is the pricing for input and output tokens?

Input tokens cost $0.15 per 1 million, while output tokens are $0.50 per 1 million. Errors and refusals incur zero charges. You only pay for actual token usage, making it a cheap LLM API for high-volume tasks.

Which payment methods do you accept?

Crypto only: USDT on TRC20 or USDC on Base, any whole amount from $20 to $500. Bonus credit applies from $50.

How do I top up my API credit using crypto?

Use USDT on TRC20 or USDC on Base for any whole amount between $20 and $500. You receive bonus credit: +5% from $50, +10% from $100, and +15% from $200. Credit never expires.

Does the API support streaming and JSON mode?

Yes. We support streaming via SSE, including token usage in the final chunk. JSON mode is available via the response_format parameter. Function calling and various sampling parameters like temperature and top_p are also supported.

What are the rate limits and concurrency constraints?

You get 300 requests per minute and 8 concurrent requests per key. The request body limit is 8 MB. Each account has one active key, and generating a new one replaces the previous key.

Get your API key instantly

Claim trial key